Find Equivalents Across Terminologies

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

Annotations only say readOnlyHint/openWorldHint/idempotentHint; the description adds substantial non-obvious behavior: match_score and rank are server-computed (upstreams don't expose comparable relevance), candidates are clustered in groups based on lexically identical titles, and absence of a group is explicitly NOT evidence of non-equivalence. It also discloses that the live fan-out has no stable cursor, so limit should be raised instead of paging, and that searches are English-only.

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 compact for the tool's complexity, front-loaded with the core purpose and use cases, followed by tightly scoped paragraphs covering scope, scoring, grouping, and language constraints. Every sentence earns its place; no filler or repetition of schema/annotations.

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 cross-terminology search tool with 4 parameters and an output schema, the description covers all practical concerns: how results are ranked/clustered, how filtering works, what the openWorldHint means here (absence of group is not negation), and when to use sibling tools for pt-BR. It even addresses pagination limitations. The output schema can handle return-value details, so nothing critical is missing.

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%, but the description elevates parameter understanding: explains limit as a per-terminology cap (not a page) with default 5 and max 10 due to no stable cursor, and clarifies how source_terminology and target_terminologies combine via subtraction. It also explains why source_terminology is useful (when you already have a code and want equivalents elsewhere), which is not apparent from the enum alone.

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 opens with 'Ranked unified search for equivalent terms across multiple medical terminologies,' giving a sharp verb+resource+scope. It further clarifies with bullets: 'Find the same concept in different coding systems', 'Compare how terminologies represent a concept', and 'Support terminology mapping and data integration'. This clearly separates it from sibling tools like icd11_search and mesh_search.

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?

Explicitly states when to use the tool ('Find the same concept in different coding systems') and gives tactical configuration guidance (target_terminologies to limit, source_terminology to exclude). It also names concrete alternatives for pt-BR content: icd11_search/mesh_search with language 'pt' and cid10_search, providing a clear when-not-to-use branch.

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