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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is handled. The description goes well beyond those: it discloses graceful degradation of LEI/FIGI enrichment, explicit `unresolved` field for failed lookups, the cascade through multiple endpoints, and the behavior of returning `figi_candidates` when a name matches several instruments. These are behavioral specifics that an agent needs to set expectations correctly, all beyond what annotations provide.

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 but information-dense. It is front-loaded with the most actionable trigger examples, then systematically covers supported types, input formats, edge cases, and fallback behavior. A few phrases could be trimmed (e.g., the parenthetical on 'non-equity instruments'), but overall every sentence contributes to accurate use. The structure (examples → types → field semantics → degradation) is logical, though it runs on in places.

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 tool with only two parameters and no output schema, the description covers every practical need: input formats, supported entity types, resolution sources, ambiguity handling, unresolved results, and graceful degradation. It even notes that ISINs resolve to the issuing legal entity via GLEIF. Nothing an agent needs to call this correctly and interpret results is missing, especially given the tool's complexity and the breadth of identifiers it returns.

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% (both parameters have descriptions), so per the rubric the baseline is 3. But the description adds substantial nuance: for `value`, it instructs to pass the entity name only, gives the example 'NEW YORK ST DORM AUTH' versus 'revenue bonds', and explains why trailing security-class words break the FIGI lookup. For `type`, it enumerates accepted inputs per type (ticker, CIK, ISIN, etc.). These details are not in the schema and materially improve 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 user query examples and states the core purpose: resolving a spoken name to canonical identifiers. It explicitly lists supported types ('company', 'drug') and the identifier families each returns (CIK/ticker, LEI, FIGI, RxCUI). It clearly distinguishes this from other tools by positioning it as the 'FIRST' step when a name needs an ID, and it picks out the non-equity resolution niche that sibling tools might not cover.

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 explicit direction: 'Use FIRST whenever you have a name but need an ID.' It provides trigger phrases ('What's the ticker for…') and details on when to use company vs drug. It also explains that it replaces 2-3 manual lookups and declines to assert on ambiguous matches, returning candidates instead — which is exactly the correct usage for an issuer name that doesn't map to a single bond. No explicit alternatives are named, but the use case is so crisply defined that exclusion is implicit.

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