Record patch verification

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

Annotations already indicate a write operation (readOnlyHint false). The description adds value by clarifying that the tool attaches outcomes rather than performing verification, providing useful behavioral context beyond the 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 two sentences, approximately 20 words, with no wasted words. The primary purpose is stated first, followed by a key behavioral note. Highly efficient and front-loaded.

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?

For a simple record operation with an output schema, the description covers the main purpose and a key behavioral trait. It lacks prerequisites (e.g., finding must be authorized) but is otherwise sufficient given the output schema handles return values.

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?

With 0% schema description coverage, the description must compensate. It mentions 'evidence' (mapping to evidence_id), 'patch outcome' (outcome), and 'authorized finding' (finding_id), but does not explain notes or provide details on what constitutes 'same-case evidence' or how to obtain the IDs. Partial coverage but insufficient depth.

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 uses specific verbs ('attach') and resources ('same-case evidence and patch outcome to an authorized finding'). It clearly distinguishes the tool's scope by stating it does not run the verification itself, which separates it from potential verification tools.

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 implies this tool is used after verification has been performed elsewhere ('does not run the verification itself'), but it does not explicitly state when to use it versus alternatives like research_record_evidence or research_assess_finding. No exclusions or direct alternatives are mentioned.

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