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

Annotations cover readOnly/idempotent/openWorld, and the description adds the fallback behavior (damped lifetime velocity) and its gating condition (20+ stars, commit in last 30 days). That fallback is genuinely non-obvious behavioral context beyond what annotations provide, though the return format and fail behavior are not covered.

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 the core purpose and the ranking metric, then the fallback qualifier. Dense and efficient, though the parenthetical '(day, week or month)' partially repeats the period enum.

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?

No output schema, so the description would ideally describe the return shape; it doesn't. But it does cover the ranking basis, the default fallback, and the data source, which is enough context for an agent to select and invoke it 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 coverage is 33%, so the schema under-documents. The description explains the 'period' concept (day/week/month via snapshots) but says nothing about 'limit' or 'type' semantics, so it only partially compensates for the coverage gap.

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 ('Fastest-growing MCP servers, skills and plugins') and the ranking metric (stars gained in period). The siblings get_tool and search_tools are retrieval tools while this one ranks by growth, so the distinction is clear from the verb 'fastest-growing'.

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?

Implied usage – an agent can infer this is for discovering trending tools ranked by growth – but there's no explicit when-to-use vs alternatives like list_best or search_tools. The choice between trending and list_best is left to inference.

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