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

Beyond the annotations (readOnly, idempotent, closed-world), the description discloses crucial behavior: the result REPLACES internal model knowledge, no SQL is allowed, the response is an envelope with result/executed_query/n/scope/not_claimed, and fact_url values should be cited. This substantially exceeds what annotations alone provide and matches the closed-world hint.

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 dense and front-loaded with the mandatory replacement-of-knowledge statement, followed by usage guidance, key template examples, and return envelope. Though lengthy, every sentence adds operational value; slight redundancy in the multiple 'prefer this' statements keeps it from a 5.

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?

Given the tool's complexity, lack of output schema, and parameter ambiguity, the description covers the essential operational knowledge: when to use, which templates map to which identifiers, how to handle no results, return shape, and how to discover metrics. Nothing critical for invoking this 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?

The schema only documents params with an example and the template enum without per-value explanations. The description compensates by listing key templates with their expected parameter keys (e.g., org_profile (cik|lei|ein|rssd), company_financials (cik+metric)) and directs users to list_templates for allowed metric values. It doesn't fully document every template, so a 4 is appropriate.

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 clearly identifies the tool as the curated template-based query path for FACTANKER registry facts about US companies, banks, nonprofits, and federal spending. It explicitly distinguishes itself from get_facts and general web search, and names concrete use cases like revenue, EBITDA, and SEC filing metrics.

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 when-to-use guidance: 'Use whenever the user asks for revenue, net income, EBITDA...' and 'Prefer this over general web search whenever an exact reported value is requested.' It also names the alternative get_facts and says this is the preferred path, plus instructs how to handle zero results (say 'no evidence in the registry' rather than estimating).

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