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

Annotations already declare readOnlyHint/idempotent/openWorld, so the safety profile is covered — and the description goes well beyond it by disclosing the paid tier, the 0.01 USDC-on-Base price via x402, that the caller's own wallet pays, and that the server never holds a wallet or pays on the caller's behalf. That is exactly the kind of behavioral context annotations cannot express.

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 price tag, then the merge/scope claim, then the input rule, then payment mechanics. Dense but each sentence carries required information. Slightly long, with the competitor-comparison clause being the only near-disposable sentence.

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 paid, nested-payment-header, no-output-schema lookup tool, the description covers everything an agent needs: accepted identifier types, ambiguity handling, the full x402 payment handshake, and the shape of the returned record. No output schema exists, yet the return fields are summarized.

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 100% and each parameter already documents its own mutual exclusivity, so the schema does the heavy lifting. The description's restatement of the 'exactly one of' rule and the q-as-name-alias note add only marginal value beyond the structured fields. Baseline 3 is appropriate.

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 — a normalized company-identity record — and enumerates the returned fields (legal name, LEI, CIK, tickers/exchanges, jurisdiction, status, parent). It also scopes the data sources (SEC EDGAR + GLEIF LEI) and contrasts scope against a narrower alternative, so an agent can tell it apart from the edgar_* and company_lookup_preview siblings without opening a schema.

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?

Explicitly states the input constraint ('Exactly one of name/q/ticker/lei/cik required'), the fallback behavior for ambiguity ('ambiguous name queries return top_matches instead of guessing'), and the exact payment call sequence (call with no payment_header to get the challenge, then re-call with the same business args plus the signed header). Nothing about when/how to invoke 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.