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

Annotations already establish the safety profile (readOnly, idempotent, not destructive), and the description adds substantial context beyond them: returned fields (similarityScore 0-1, matchExplanation), the signals used for matching, auth requirements, and that calls consume the monthly search allowance with free-plan listing limits still applying. This quota/auth disclosure is exactly the kind of behavioral context annotations cannot convey.

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?

Front-loaded with purpose and mechanism, and each sentence is informative. However, the three trailing sentences about account access and quota ('Available to authenticated free and paid accounts... Free-plan listing-access limits still apply. Counts toward your monthly searches.') overlap and could be condensed into one.

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 steps in to describe return values (similarityScore and matchExplanation). Combined with the annotations covering safety, and the auth/quota disclosure, an agent has everything needed to invoke this correctly.

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 100%, so both parameters (opportunity_id and limit) are already documented in the schema, including defaults and max. The description implies opportunity_id semantically ('similar to a given one') but adds no format or constraint detail beyond the schema. Baseline 3 is appropriate when the schema carries the parameter burden.

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 (find), resource (opportunities), and the mechanism (semantic similarity/vector embeddings). It explicitly distinguishes itself from keyword-based siblings like search_grantsplus by noting it finds 'conceptually related opportunities, not just keyword matches.' An agent can tell exactly what this does versus the sibling search 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?

Gives a clear trigger condition: 'Useful when user likes one result and wants more like it,' which maps cleanly to the required opportunity_id input. It does not name an explicit alternative tool or state when NOT to use it (e.g., versus get_opportunity), so it stops short of full when/when-not guidance.

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