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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description usefully adds pagination behavior (limit default 20, max 100, total/truncated/next_offset) and the shape of each returned item (receipt_url, counts_as_verified, limits), which substitutes for the absent output schema.

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?

Two dense sentences, front-loaded with the filter surface and then the result/pagination contract; no filler. Internal shorthand codes (cd-1b) add slight noise but each sentence carries real information.

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 9-parameter read-only search with no output schema, the description supplies the return shape and paging contract that would otherwise be missing. Remaining gaps are minor: result ordering/ranking and whether text search is substring or tokenized.

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 33% across 9 parameters, so the description must compensate. It does explain authz_ref (sha256 of an authorized plan) and the depends_on reverse-lookup semantics beyond the schema, and covers limit/offset via the pagination note, but q, agent, status and subject are only name-level with no added meaning (matching rules, exact vs partial, allowed values).

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?

States a specific verb+resource ('Search claims') and enumerates the exact filter axes (text, subject, agent, status, authz_ref, depends_on), so an agent knows precisely what surface it queries. It does not name a sibling alternative, but no other sibling is a search tool, so the ambiguity risk is low.

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?

Usage is implied through the filter enumeration rather than stated: an agent can infer to use authz_ref to find claims committed to a plan and depends_on for reverse lookup. There is no explicit when-to-use/when-not or pointer to a sibling tool for related tasks.

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