Search APIs and MCP servers

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

With no annotations, the description carries the full burden and does so: it explains ranking inputs (operation fit, evidence, free plan, card/auth effort, bulk limits, explicitly excluding budget and region), the meaning of match labels, mcp_fit, review vs fit distinction, and the provisioning caveat ('Services work only once a human has provisioned credentials'). It also states the empty-result semantics and the retry path.

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?

Purpose and trigger are front-loaded, then match/ranking, then each filter family. It is dense and long for a description, but given 15 parameters and no output schema most sentences carry distinct semantic load rather than repeating structured fields. A tighter grouping of the ratings/sort sentences would improve readability.

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 15-parameter, zero-required discovery tool with no output schema, the description covers the missing return-value semantics (match, mcp_fit, ratings.usage, ratings.issues, reviews_summary) and the operational caveat about human credential provisioning. An agent has enough to search, filter, and interpret results 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 high (93%), so the baseline is 3, but the description adds real meaning for filters beyond the schema: free_plan.kind (free_tier lasts vs trial one-off), what ratings.usage and ratings.issues actually measure, and how sort ties are broken. It also explains non-schema result fields (match, mcp_fit, reviews_summary), compensating for the absent output schema.

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 states a specific verb and dual resource ('Find a third-party API or MCP server') and frames the search scope ('among 300+ catalog entries with a last-checked date'). It is clearly distinguishable from siblings list_categories, get_api and get_reviews, which handle taxonomy and detail retrieval rather than discovery.

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?

It gives an explicit trigger condition ('an operation you cannot do with your model, built-in tools or currently connected tools'), a concrete self-check ('if you cannot name the tool that does the operation... search'), a second trigger (service-side failures like auth/quota/billing/region), and an explicit exclusion ('not after a malformed request of your own'). This is textbook 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.