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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds materially new behavior: it names the returned fields (candidates, legal names, jurisdictions, statuses), warns that name matching is not identity certification and that LEI status is not a soundness attestation, and discloses a paid, metered call ($0.0051 USDC via x402 on Base mainnet). The payment requirement is exactly the kind of precondition an agent cannot infer from annotations or schema.

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 action and resource, followed by return values, workflow, caveats, pricing, and an example — a sensible priority order with no filler. The caveat and pricing sentences are dense and pack multiple clauses each, but every one carries actionable signal.

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 two-parameter search tool with an output schema, the description supplies everything else an agent needs: what comes back, how it chains into lookup_lei, the interpretive limits of a match, and the paid-call precondition. Nothing essential is left out relative to the tool's complexity.

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 0%, so the description carries the burden here, and it does only partial work: it says "supply query; optionally limit results" and gives a concrete example payload, which clarifies the shape of both parameters. It never states that limit is an integer bounded 1–20 with a default of 10, nor what form a valid query string takes beyond "legal-entity name" (min/max length, partial-match behavior). Adequate but with real gaps for a 0%-coverage 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?

"Find candidate LEIs by legal-entity name in GLEIF's global LEI index" gives a specific verb (find/search), a specific resource (LEI), and the source registry. It is explicitly a candidate-search tool, which separates it from lookup_lei (exact-record retrieval) and from search_company in the sibling list.

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?

The description lays out a concrete workflow: supply a query, pick a candidate, verify it, then call lookup_lei for the full record. That is clear routing guidance to the natural alternative. It stops short of stating when NOT to use it (e.g., when the LEI is already known, or versus search_company for non-LEI entity search), so it falls short of a 5.

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