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

The description reveals many behavioral traits beyond the annotations: internal cascading through several lookup endpoints, graceful degradation when GLEIF/OpenFIGI is unavailable, assertion-free behavior for ambiguous matches (returns figi_candidates), explicit unresolved identifier reporting, and the fact that non-ticker instruments DO resolve. These details are not present in the annotations and materially shape the agent's expectations.

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 information-dense with no filler — every sentence contributes a distinct fact, from supported types to edge cases. It front-loads user utterances and the core instruction. The heavy use of parentheticals makes it slightly less skimmable for an agent, but the content justifies the length.

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?

With no output schema, the description must explain what the tool returns. It does this thoroughly: it names the identifier fields, the ambiguous-match behavior (figi_candidates), the unresolved field, and the degradation/failure modes. It also covers input variants and an edge case (ISIN-to-LEI mapping for non-US issuers). Nothing an agent needs to select and call the tool correctly is missing.

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?

Although schema coverage is 100%, the description adds substantial semantic value: it maps `type` to concrete output fields for company (CIK, ticker, LEI, FIGI) and drug (RxCUI, ingredient, brand), and for `value` it provides formatting rules (pass entity name only, bond issuer exactly as printed, never the noun phrase). This goes well beyond the terse schema descriptions and prevents common errors.

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 example queries ('What's the ticker for…', 'find the CIK for…') then states the precise action: resolve a user-spoken NAME to canonical/official identifiers. It also names the resource these identifiers serve ('other tools require as input') and differentiates from siblings by declaring 'Use FIRST whenever you have a name but need an ID.' This gives a specific verb, resource, and clear positioning.

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?

It explicitly provides a usage rule: 'Use FIRST whenever you have a name but need an ID.' It gives rich usage context, including which input formats are accepted (ticker, CIK, ISIN, name) and which are not (the full noun phrase for bonds). It also indicates the tool replaces 2-3 manual lookups, implicitly telling the agent to prefer this over chaining multiple other tools.

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