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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint false, but the description adds substantial behavioral context: it cascades through multiple lookup endpoints internally, degrades gracefully (if GLEIF or OpenFIGI is unavailable, EDGAR still returns), returns `figi_candidates` when ambiguous without asserting a result, and lists unresolved identifiers explicitly under `unresolved`. This goes well beyond the annotations and gives the agent a clear model of what happens during execution. No contradiction with annotations exists.

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?

The description is long (several paragraphs) but extremely front-loaded: the first sentence delivers the core purpose and examples, and the 'Use FIRST' instruction appears early. It then systematically covers supported types, edge cases, and degradation. While every sentence adds value, the length could be slightly trimmed without loss. The structure is logical (overview → types → behavior → fallback), and it avoids redundancy, but it is not concise in the strict sense. Given the tool's complexity, this is appropriately sized, though it could be tightened.

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?

Despite having no output schema, the description fully covers return behavior: it mentions `figi_candidates`, `unresolved` for failures, and labels each identifier with its source. It explains handling of ISINs, non-US issuers, and non-equity instruments. It also notes graceful degradation and that it replaces multiple manual lookups. For a tool with two parameters and considerable complexity, nothing essential is missing; the agent can confidently invoke it.

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?

The schema already provides descriptions for both parameters (coverage 100%), so a baseline of 3 applies. However, the description enriches parameter meaning significantly: for `value`, it clarifies that for a bond you must pass the ISSUER exactly as printed, never the full noun phrase, and explains the reason. It also specifies that for `type='company'` the input can be ticker, CIK, ISIN, or name, and for `type='drug'` a brand or generic name. This additional guidance goes beyond the schema's plain descriptions and directly influences correct invocation.

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 opens with concrete natural-language examples ('What's the ticker for…') that make the tool's purpose unmistakable: it maps a spoken name to official identifiers (CIK, ticker, LEI, RxCUI). It explicitly states it is the tool to use 'whenever you have a name but need an ID,' which distinguishes it from sibling tools like entity_profile that likely operate on existing IDs. The purpose is specific, actionable, and clearly separated from other 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?

The description gives a direct directive: 'Use FIRST whenever you have a name but need an ID.' It then specifies exactly what inputs are accepted per type and even warns against passing the full noun phrase for bonds, explaining the reason (FIGI lookup matches instrument names). It covers when to use it (name→ID) and implicitly when not (when you already have an ID), and it mentions that it replaces 2-3 manual lookups, indicating efficiency. No other tool is named, but the guidance is unambiguous.

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