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

No annotations are present, so the description carries the full burden. It discloses the method (fetches advertised tools, statically analyzes), the output (findings + 0-100 risk score + verdict), and importantly the cost ($0.005 USDC per scan via x402) and HTTP variant pricing. This goes well beyond a minimal description, though it does not explicitly state side effects like whether it makes external network requests (implied by 'fetches') or any rate limits.

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 four sentences and dense with information, but every sentence contributes value: purpose, method, outputs, and cost. It is not verbose or repetitive, yet it is longer than the ideal two-sentence format. No waste, but not maximally concise.

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?

For a one-parameter tool with no output schema, the description is quite complete: it describes the analysis scope, the return format (findings + risk score + verdict), and the cost. It lacks explicit error-handling or timeout information, but those are not critical for this tool's complexity. The presence of the preview sibling suggests a few details about when to use the full server scan vs preview could enhance completeness, but overall it is sufficient.

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 input schema already has 100% coverage for the single 'url' parameter with a clear description ('Target MCP server endpoint URL to audit'). The description adds minimal additional semantic value beyond restating the URL target, so the 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 verb 'Security-audit' and the resource 'target MCP server', with specific focus areas (prompt-injection/tool-poisoning) and deliverables (findings, risk score, verdict). It is specific and differentiates from other non-scan tools, but it does not explicitly contrast with the sibling 'scan_mcp_preview', so it misses the full sibling differentiation criterion.

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?

There is no explicit guidance on when to use this tool versus alternatives like scan_mcp_preview. The description implies its use for a full security audit but does not state exclusions, prerequisites, or when a preview would suffice, leaving the agent without clear decision criteria.

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