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

Beyond the annotations (readOnlyHint=true, openWorldHint=true, destructiveHint=false), the description adds valuable behavioral context: it explicitly confirms no browsing/fetching/verification, mentions the output is a 'stable' table, and discloses the cost and payment method ($0.05/call, x402 USDC on base). This enriches the annotation information without contradiction.

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 two sentences plus a pricing tag, front-loaded with the core action and output. Every clause adds meaningful information: the action, the output components, the explicit non-actions, and the cost. There is no redundancy or filler.

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 moderate complexity (arrays with multiple fields, no output schema), the description is complete: it explains what the output contains (counts, limitations, digests), what it does NOT do, and the schema fully documents the input fields and constraints. Annotations cover safety, and the description clarifies behavior sufficiently for an agent to select and invoke it 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?

The schema already provides 100% description coverage for both parameters (rows and schemaVersion) with detailed field constraints and semantics. The tool description does not add parameter-specific meaning; it only refers generally to the evidence packet and formatting, so a baseline score of 3 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 states the tool's function: transforming a buyer-owned evidence packet into a stable citation table with specific components (bounded Markdown citations, host/source counts, limitations, digests). It also distinguishes itself by explicitly negating browse, fetch, verify, rank, or enrich actions, setting it apart from potential sibling tools.

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 implies when to use the tool (when you have a small buyer-owned evidence packet) and clearly states when-not (it does not browse, fetch, verify, rank, or enrich). However, it does not explicitly name alternative sibling tools, so it stops short of the full 5 criterion.

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