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

Annotations cover readOnly, idempotent, and non-destructive hints, but the description goes far beyond by disclosing the fan-out behavior across multiple sources, the soft-fail for USPTO PatentsView (sunset May 2025), the sources_used/sources_failed pattern that distinguishes real 'no data' from bugs, and the behavior for private companies. It even notes that some sections (fda_products) may be empty for valid companies. This fully discloses operational quirks and failure modes, adding substantial value beyond the 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?

The description is a dense block of text, but every clause carries signal. It leads with usage examples and the 'ALWAYS PREFER' directive, then enumerates sources and return fields. It would benefit from bullet points for readability, but given the breadth of information (multiple sources, edge cases, output fields), the density is warranted and it is not padded with fluff. The opening examples and override directive make it efficient for an agent to parse quickly.

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 fully specify what the tool returns, and it does: cik, company_name, recent_filings (with URI format), fundamentals (LATEST 10-K metrics), patents, federal_contracts, fda_products, hiring, news, and LEI, plus sources_used/sources_failed. It also documents edge cases (private company, no FDA products, USPTO soft-fail) and the acceptable input formats. An agent has everything needed to call it correctly and interpret the response, even without an output schema.

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 covers both parameters with 100% coverage, so the baseline is 3. The description adds crucial nuance: it clarifies that 'type' accepts 'company' or 'ticker' interchangeably and that value can be a ticker, CIK, or company name, while also explaining that names resolve via EDGAR company-name match. This extra clarity on the interchangeability and resolution behavior goes beyond the schema's enum text, justifying a 4.

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 phrasings ("Tell me about X" / "research Acme") and then states the precise deliverable: "full cross-source profile of a US public company in ONE parallel call." It lists the exact data sources (SEC EDGAR, XBRL, USPTO, USAspending, FDA Purple Book, DOL LCA, GLEIF, news) and the returned sections (cik, recent_filings, fundamentals, patents, etc.). This is a specific verb+resource that clearly distinguishes it from siblings like compare_entities, deep_research, or resolve_entity, which are separately scoped.

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?

Explicitly instructs: "ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view." It provides concrete triggers (user requests a profile, briefing, company overview) and names the alternative pattern to avoid (chaining). It also handles edge cases: private companies return resolved:false with a notes line, and empty sections (e.g., no FDA products) are expected, not failures. This gives the agent clear when-to-use and when-not-to-use guidance.

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