{"data":{"id":"10.5281/zenodo.23752436","type":"dois","attributes":{"doi":"10.5281/zenodo.23752436","prefix":"10.5281","suffix":"zenodo.23752436","identifiers":[{"identifier":"oai:zenodo.org:23752436","identifierType":"oai"}],"alternateIdentifiers":[{"alternateIdentifierType":"oai","alternateIdentifier":"oai:zenodo.org:23752436"}],"creators":[{"name":"Armani, Ryan","nameType":"Personal","givenName":"Ryan","familyName":"Armani","affiliation":["Independent researcher"],"nameIdentifiers":[{"nameIdentifier":"0009-0005-9964-6841","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"Tool Errors: Measuring Safe Recovery from Ambiguous API Failures"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"tool errors"},{"subject":"fault injection"},{"subject":"safe retries"},{"subject":"idempotency"},{"subject":"agent evaluation"}],"contributors":[],"dates":[{"date":"2026-10-29","dateType":"Issued"}],"language":null,"types":{"ris":"GEN","bibtex":"misc","citeproc":"article","schemaOrg":"CreativeWork","resourceType":"","resourceTypeGeneral":"Preprint"},"relatedIdentifiers":[{"relationType":"IsSupplementedBy","relatedIdentifier":"https://github.com/pooriaarab/benchmark-tool-errors","resourceTypeGeneral":"Software","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.23752435","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":null,"rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"An API error does not establish whether an operation took effect. Tool Errors measures safe recovery through stateful fault injection and replay-based scoring. Its 40 public episodes cover 6 fault families across 4 domains. We execute 4960 episodes using scripted controls and a simulated status-read omission sweep. The reference and response-aware controller each reach full credit on 40/40 tasks (95% Wilson interval 91.2-100.0%). Removing reads in a simulated ablation leaves 7/40 full-credit tasks (8.7-31.9%). At simulated read-omission probability 0.5, the mean full-credit fraction is 53.8% (50.6-56.9%, seed bootstrap). These are checks of the evaluation design, not trained-model results. No hosted model, human study, or production deployment is evaluated.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"xml":"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","url":"https://zenodo.org/doi/10.5281/zenodo.23752436","contentUrl":null,"metadataVersion":2,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"viewsOverTime":[],"downloadCount":0,"downloadsOverTime":[],"referenceCount":0,"citationCount":0,"citationsOverTime":[],"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":1,"created":"2026-10-29T03:17:45.000Z","registered":"2026-10-29T03:17:46.000Z","published":"2026","updated":"2026-11-07T05:40:22.000Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}},"provider":{"data":{"id":"cern","type":"providers"}},"media":{"data":{"id":"10.5281/zenodo.23752436","type":"media"}},"references":{"data":[]},"citations":{"data":[]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[]},"versionOf":{"data":[{"id":"10.5281/zenodo.23752435","type":"dois"}]}}}}