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

Beyond the readOnlyHint/destructiveHint annotations, the description discloses the mandatory citation behavior, the exact markdown format using item.url, the preference for verbatim quotes over paraphrase, and a verification workflow. This is substantial behavioral context that annotations alone do not provide.

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?

Three sentences carry a dense but relevant payload. The field list is compact, the critical CITATION REQUIRED directive is prominently emphasized, and there is no filler. Slightly dense, but every sentence earns its place.

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?

With no output schema, the description must explain return values, and it does: card structure, URL behavior, citation format, filtering, and verification path. An agent can invoke this tool correctly and process its results without needing to infer unstated behavior.

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 baseline is 3. The description reiterates the 'any match' semantics for codes and the lens enum, but these are already in the schema. It adds little parameter-level meaning beyond the structured definitions.

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 begins with 'List L2 coded claim-cards' and enumerates the exact fields included, making the tool's purpose explicit and distinct from sibling read tools like insights_read or interviews_read. The resource (L2 coded claim-cards) is unambiguous and the filtering options are stated.

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 states the filtering dimensions and provides an explicit alternative: 'Verify with interviews_read action=transcript around_chunk_index when a wider quote window is needed.' This gives clear when-to-use guidance for a related sibling. It does not contrast with search or insights_read, but the primary use case is well-defined.

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