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

Beyond the readOnlyHint/idempotent annotations, it discloses ranking order (exact name, then publisher, then tags/description), that official and verified results are boosted, and that duplicates are merged. It omits key-gating limits and pagination behavior, though the schema's parameter descriptions cover those.

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 tight sentences, front-loaded with what the tool finds before the ranking parenthetical and the next-step call. The ranking clause is dense but each part 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?

For an 11-parameter search tool with a full schema and an output schema, the description covers selection, ranking, and the follow-up action without needing to explain return values. Only the multi-step search-then-install loop is left slightly implicit.

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 every parameter already carries its own explanation. The description restates the query dimensions but adds little syntax or format detail beyond the schema, so the baseline 3 applies.

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 and resource ('Find MCP servers') plus the three searchable dimensions (product name, publisher, topic). It also implicitly distinguishes itself from get_server/compare_servers by framing the output as 'compact cards' and pointing forward to get_install.

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 workflow cue: search here, then 'call get_install next'. It does not explicitly contrast with recommend_servers or list_categories, which are the nearest siblings an agent might pick instead, so the alternatives guidance is incomplete rather than absent.

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