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

Annotations already declare a non-read-only, non-idempotent, non-destructive write, so the safety profile is covered. The description adds the useful distinction that a link can be proposed (agent_proposed by default) or recorded, but says nothing about duplicate handling, what happens to an existing link, or required permissions.

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?

A single front-loaded sentence with no filler. It is efficient, though arguably too terse for a five-parameter write operation.

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 write tool with five parameters, no output schema, no enum hints, and zero schema description coverage, the description omits critical call-time details: valid stance values, the meaning of assessment, and duplicate-link behavior. It is not complete enough to invoke confidently.

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 0%, so the description must carry the burden. It maps 'retrieval' to retrieval_id and 'claim' to claim_id and gestures at stance ('how ... relates'), but leaves the allowed stance values, the note field, and the assessment field entirely undocumented.

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 names a specific action (linking a retrieval to a claim) and identifies both resources, so the agent knows the general operation. However, it does not differentiate from siblings such as add_evidence_to_collection or create_claim, which also relate evidence to claims.

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 words 'propose or record' imply two workflow modes, but there is no explicit guidance on when to use this tool versus add_evidence_to_collection, create_claim, or search_evidence. No prerequisites or exclusions are stated.

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