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

Annotations already declare readOnly, idempotent, non-destructive, and open-world behavior, so the bar is lower, yet the description adds substantial context beyond them: 1-hour result caching (<5ms hits), $0.02 per call, 5 free calls per agent_id, failed calls never charged, and that quota exhaustion returns a payment-required quote rather than a fatal error. The only slight gap is that it doesn't spell out latency for cache misses or failure semantics beyond billing.

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?

Front-loaded with purpose, then structured WHEN TO USE / WHEN NOT TO USE / PARAMETER INTERACTIONS blocks, and every section maps to a real decision. It is verbose and restates payment mechanics (free calls, top-up, retry) in both the pricing sentence and the parameter block, which costs a point.

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 an output schema already exists, the description needn't explain return values, and it covers everything else an agent needs: pricing/quota mechanics, payment failure handling, caching behavior, and parameter routing. Complete for a paid, cached audit tool.

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%, so the baseline is 3, but the PARAMETER INTERACTIONS block adds genuine semantics the schema does not: when to omit agent_id/tx_hash (free trial) versus supply an agd_pass_ key or on-chain tx_hash for paid execution. This meaningfully clarifies the relationship among the three parameters.

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 compound verb (audits/compiles) and resource (any live MCP server URL or GitHub repo), naming the TDQS rubric and the concrete deliverables (schemas, A2A Agent Cards, x402/MPP configs). This clearly separates it from the sibling get_agent_wallet_status, which is also referenced by name.

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?

Explicit WHEN TO USE / WHEN NOT TO USE sections, plus a named alternative (get_agent_wallet_status for quota/balance) and a precise routing rule for the sibling. The trial-vs-paid condition also tells the agent when to supply or omit each parameter.

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