evidence_create

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses important behavioral traits beyond annotations: the tool returns an uploadFileUrl for INTERNAL custody, describes the manual vs. convenience upload process, warns about potential false errors (EvidenceCreateError), and mandates verification. This adds significant context over the annotations (idempotentHint=true, readOnlyHint=false, destructiveHint=false). No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but well-organized, with clear sections for requirements, flows, and warnings. It front-loads the core purpose and prerequisites, then provides detailed flow instructions. While every sentence adds value, it could be slightly more concise by grouping repetitive warnings.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (8 parameters, multiple flows, no output schema), the description is remarkably complete. It explains the return value (uploadFileUrl), outlines complete steps for each flow, and addresses edge cases like retry and error handling. Without an output schema, it compensates fully by describing expected behavior and post-call verification.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents each parameter. The description adds value by explaining the purpose of each parameter in the context of different flows (e.g., fileUrl for convenience, custodyType for storage vs. hash-only). It clarifies that id must be a fresh UUID v4 and hash must be computed beforehand, enriching understanding beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it registers a new evidence record inside an evidence group, distinguishing it from sibling tools like evidence_list, evidence_get, and evidence_seal. It specifies the verb 'Registers' and the resource 'evidence record', making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidelines on when to use each flow (INTERNAL, EXTERNAL, convenience), including prerequisites (evidenceGroupId, caseFileId) and exclusions (do not reuse failed IDs, do not seal before upload). It also mentions verification steps and error handling, offering clear context for agent decision-making.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.