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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered; the description adds substantial behavioral context beyond this: match-mode mechanics (exact-normalized → all-tokens-present → Jaro-Winkler), the raw 0–1 score semantics and token-coverage ordering, paging behavior via totalAvailable/hasMore/nextOffset, and the critical caveat that results are candidates to confirm rather than authoritative. No contradiction with annotations.

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?

At roughly 120 words it is long, but every sentence earns its place for a 7-parameter tool with multiple matching modes and paging. The core purpose is front-loaded in the opening sentence, and the matching-mode detail, paging mechanics, and confirmation caveat each carry distinct information. Slightly dense, but justified by complexity.

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 complex, 7-param tool with an output schema, the description is remarkably complete: it covers purpose, both match modes plus the auto fallback, scoring semantics, paging, and the non-authoritative nature of results. Since an output schema exists, return-value documentation is already handled. The only minor absence is explicit guidance on when to prefer this over sanctions_screen_name, which does not meaningfully detract.

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 100%, so the baseline is 3, but the description adds genuine value on top: it defines the 'auto' behavior not present as an enum value in the schema ('fuzzy mode (or auto when strict is empty)'), clarifies what minScore means ('Jaro-Winkler floor for fuzzy hits'), explains the matchMode semantics beyond the enum labels, and ties offset to the returned nextOffset/hasMore paging contract.

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 ('Resolve'), resource (company/organization name), and output (candidate GLEIF LEIs), plus an optional jurisdiction qualifier. It also positions itself relative to siblings by naming sanctions_get_entity and sanctions_trace_ownership as the consumers of its output, and its candidacy caveat ('name resolution is a candidate ranking, not an authoritative identification') clearly distinguishes it from look-up tools.

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?

Provides clear context: this is the resolution step that produces the stable identifiers get_entity and trace_ownership key off, and it warns results must be confirmed, not trusted. It explains strict vs fuzzy mode behavior including the 'auto when strict is empty' fallback. It does not, however, give explicit exclusions versus siblings like sanctions_screen_name, so an agent must infer when resolution rather than screening is appropriate.

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