Dredd MCP

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains that REVIEW does not mean safe, that ALLOW is only returned after actual resolution and scanning, and that known_to_us and dep_graph.scanned must be checked. It also mentions the HMAC-signed response, adding security context. These are beyond what annotations would typically provide and give the agent a clear behavioral model.

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 front-loaded with the core purpose, then provides critical behavioral caveats and usage guidance. Each sentence adds substantive information about verdict semantics or invocation guidance. It's longer than a minimal description, but every sentence earns its place, and the structure logically flows from purpose to outcomes to usage.

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?

There is no output schema, so the description must explain return values and semantics. It does so thoroughly: lists the four verdicts, details evidence and HMAC signing, explains the meaning of REVIEW and ALLOW, and clarifies when to trust the result. It also gives usage context. This is complete for a security-check 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?

The schema already provides 100% coverage with clear descriptions for each parameter (tool, server, version). The description does not add parameter-level details, but the baseline of 3 is appropriate because the schema does the heavy lifting. It implicitly connects parameters to the overall purpose (e.g., 'server' maps to server-level reputation) but doesn't go beyond that.

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 with a specific verb ('Pre-flight security verdict') and identifies the resource ('MCP server invocation'). It also outlines the output categories (BLOCK/ADVISORY/REVIEW/ALLOW), which distinguishes it from any generic security tool. Though there are no sibling tools to differentiate from, the description is not a tautology and conveys a distinct purpose.

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 instructs to use this tool 'BEFORE invoking any other MCP server tool' and calls out the specific context of servers installed from outside the official registry. It also explains what REVIEW means ('do-not-proceed-blindly') and what ALLOW implies, giving clear guidance on interpreting results. This is strong usage direction.

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