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

The description significantly adds context beyond the readOnlyHint annotation. It details that the tool is cost-zero, operates only on the declared tool surface (from tools/list), flags state-changing tools without machine-readable annotations, provides an exposure tier, and is ed25519-signed and offline-verifiable. It also clarifies it is an observation, not a security claim. No contradiction with annotations.

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 relatively concise for the amount of information conveyed, but it uses all-caps for emphasis (DEFENSIVE, OBSERVATION, NOT) which aids clarity. It front-loads key purpose and usage intent. A minor improvement could be to shorten some run-on sentences, but overall it is well-structured and reasonably sized.

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?

The description covers what the tool does, how it works (using tools/list, flagging unannotated state-changers, detecting new exposures), and its output characteristics (ed25519-signed, offline-verifiable). However, it does not specify the exact format or structure of the returned profile, which might be expected given the absence of an output schema. Still, it provides a comprehensive high-level overview sufficient for agent understanding.

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 has one parameter 'url' with a description stating 'The MCP server endpoint URL (https) to profile'. The tool description does not add new semantic information about this parameter beyond what the schema already provides. With 100% schema coverage, a baseline of 3 is appropriate, as the description does not elaborate on URL format or validation rules.

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 performs a 'DEFENSIVE pre-call check for one public MCP server' that classifies declared tool surface into capability-risk classes and identifies newly exposed higher-risk classes. It distinguishes itself from siblings by specifying it is an observation of the declared surface, not a vulnerability scan, and differs from tools like 'verify_mcp_cert' or 'audit_mcp'.

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 explicitly tells when to use the tool: 'Use it before wiring an untrusted MCP into an agent.' It also clarifies what the tool is not ('NOT a vulnerability/malware scan and NOT a claim the server is unsafe'), providing clear usage boundaries. While it does not explicitly name alternative tools for vulnerability scanning, the context of 'defensive pre-call check' implies its specific use case.

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