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

Annotations cover only readOnlyHint and openWorldHint; the description adds substantial context beyond that: truncation behavior (free tier returns only the first 25 names), what the paid tier adds (full named list with evidence), and the exact cost and payment mechanism ($0.25/call over x402 in USDC on Base, or free with a Radar/Ontology key). Cost and result-capping are exactly the operational facts an agent needs before deciding to call.

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?

Two sentences, front-loaded with the resource and followed by the mode/cost rules; the parenthetical rule examples are dense but earn their place by showing the id conventions. Pricing is repeated in both the description and the schema, which is mild redundancy but justified given the unusual x402 payment model.

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?

No output schema exists, and the description carries that burden reasonably: it tells the agent to expect counts, organization names, and (on the paid path) supporting evidence, plus the 25-name ceiling. It stops short of describing the record fields for each organization or how evidence is formatted, which leaves some uncertainty about the exact return shape.

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 description coverage is 100% and the full parameter's description already spells out the pricing, evidence, and 25-name cap, so the description largely restates schema content. It does add the semantic coupling that full=true only matters when rule_id is supplied ('add full=true'), which is a small value-add over the schema's 'With rule_id' phrasing.

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 specific verb and resource ('List the federal rules Tensorust models') and immediately grounds it with five concrete rule examples and the payload shape (counts plus first organizations). This reverse-lookup direction (rule -> organizations) is clearly distinct from sibling tools like lookup_organization and search_organizations, so an agent can route without opening the schema.

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?

Gives clear mode selection: omit rule_id to list all rules, pass rule_id for a single rule, add full=true for the complete named list with evidence. It does not explicitly state when to prefer this over the organization-centric siblings (e.g., 'use this to find who a rule touches, not to look up a company'), so the alternative-routing is implied rather than stated.

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