evidence_update

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

Beyond the annotations (which only indicate non-read-only, non-idempotent, non-destructive), the description discloses that file content and hash are immutable and that changed files require re-registration. It also specifies that an evidenceId must come from prior registration or generation. This adds meaningful behavioral context, though it does not go into partial-update semantics.

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 exceptionally concise, with two sentences that front-load the core purpose, then state the key constraint and prerequisite. Every sentence provides essential information with no filler.

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?

The description covers the core operational context (single evidence, editable metadata, immutable content, evidenceId provenance) but lacks explanations for the nested deletion fields, metadata structure, and return behavior. Given no output schema and only 14% parameter coverage, the description is adequate but not fully complete for a 7-parameter tool.

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 description coverage is only 14% (only evidenceId is described), so the description must compensate for the other six parameters. It broadly says 'editable metadata' and gives examples, but does not explain the semantics of deletionDate, deletionType, createdBy, custody, or metadata structure. This leaves substantial gaps for the agent to infer parameter meaning.

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 states a specific verb ('Updates'), a specific resource ('a single evidence's editable metadata'), and a specific identifier ('by evidenceId'). It clearly differentiates from sibling tools like evidence_update_bulk by emphasizing 'single' and clarifies what is immutable (file content and hash), 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?

The description explicitly says when to use the tool (updating editable metadata) and when not to use it (when file content changes, re-register a new evidence). It also states a prerequisite for obtaining the evidenceId. It stops short of explicitly naming a sibling alternative for bulk updates, but the 'single' qualifier and sibling name make that implicit.

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