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

Annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) already cover the safety profile, and the description adds substantial behavior beyond that: graceful degradation ('if GLEIF or OpenFIGI is unavailable, the EDGAR identifiers still return'), internal cascading through several endpoints, parent/ultimate-parent/children ownership data, the ISIN-to-LEI path for non-US issuers, and the pipeworx://rxnorm/concept/{rxcui} citation format for drugs. This is exactly the failure-mode and fallback context an agent needs before calling.

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 definition is long, but nearly every sentence earns its place — the non-equity-instruments note, the ISIN mapping, and the degradation caveat all carry information an agent would otherwise lack. It front-loads the purpose and the 'use FIRST' directive before the type details. It loses a point for being a dense single block of nested parentheticals that is harder to parse than necessary.

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 carries the responsibility for return-value semantics, and it delivers: it enumerates returned identifiers per type (CIK, ticker, company_name, LEI, FIGI, ownership; RxCUI, ingredient, brand, citation) and explains fallback behavior when upstream sources fail. Between the annotations, the rich parameter schema, and this description, an agent has what it needs to select and invoke the tool correctly.

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% and the 'value' parameter description is already rich (entity-name-only rule with the NEW YORK ST DORM AUTH example). The description adds meaning the schema lacks: ISIN as a third accepted input form for company, the FIGI routing rule (exact ticker map vs name search), and the per-type return payloads. That lifts it clearly above the high-coverage baseline of 3.

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 precise verb+resource: resolve a user-spoken NAME to the canonical/official identifiers other tools require as input. The quoted example queries ('what's the CIK for…', 'who owns X', 'is X a subsidiary of Y') immediately ground what counts as a resolution task, and the two supported types ('company', 'drug') delimit scope. It is clearly differentiated from siblings like entity_profile, which consume the IDs this tool produces.

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 an explicit directive — 'Use FIRST whenever you have a name but need an ID' — strong when-to-use guidance for an entry-point resolver. It also spells out accepted input forms (ticker, CIK, ISIN, or company name; brand or generic drug name) and which entities resolve, including non-equity instruments. It stops short of naming sibling alternatives or explicit when-not-to-use conditions, so it is not a 5.

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