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

Annotations cover only the safety profile (readOnly, idempotent, non-destructive, closed-world); the description adds far more: cost model (price / works.rate, thin rows filled at job average), ordering semantics for `prefer`, default page size and 200 cap, the empty-items + warnings signal, priceHint behavior when maxPriceMicros over-filters, and the jobInputs/pinned-tool-id caveat.

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 is front-loaded and nearly every clause carries real information, but it is delivered as one dense run-on paragraph with tangled parentheticals (e.g. the thin-row averaging aside) and a stray "looot:" prefix. Routing advice, pagination, and return-shape details are interleaved rather than ordered, making it harder to scan than its content warrants.

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 exists, and the description compensates fully: it enumerates the row fields (endpointId, provider, capability, estimatedPrice, priceBasis, costPerSuccessUsd, works{rate,runs,p50Ms,thin}, access, async, credential), explains what detail "full" adds, and describes pagination and the warnings/priceHint edge cases. It also closes the loop with a next action (inspect the endpointId).

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?

With 0% schema description coverage and a 10-key nested filters object, the description carries the load and does well for query, filters.capability, limit/offset pagination, `prefer` (all four enum values with semantics and the default), detail "full", and filters.maxPriceMicros. It gives no meaning for filters.mock, hidden, keyless, category, platform, provider, verified, or includeUnavailable, so an agent must infer half the filter surface from bare key names.

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 concrete verb and resource — "free search of the data API catalog by job" — and positions itself as "the first step to find an endpoint", which is a distinct job from siblings. It explicitly routes to catalog_overview, capability_request, discover_smart and inspect, but never addresses the near-identically named sibling `search_catalog`, leaving an agent to guess which of the two to call.

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?

Explicit when-to-use (first step before inspect), how to invoke both modes (plain-words query vs. filters.capability, with query optional when a filter is set), and two concrete fallbacks: capability_request when no endpoint does the job, discover_smart when no confident match exists. Exclusions and alternatives are named rather than implied.

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