audit_mcp_config

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

With no annotations, the description carries the full burden and does so well: it explicitly states 'Nothing is read from disk; pass the text', clarifies the input mode, and discloses that the output consists of findings 'each with the fix'. This gives an agent an accurate safety model without needing annotation hints.

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 dense, but every clause earns its place: trigger, input sources, security categories, fix output, and no-disk-read warning. The long checklist is justified because it defines the tool's scope precisely, and the critical 'pass the text' instruction is clearly stated.

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 a single string parameter, no output schema, and no annotations, the description is complete enough: it tells the agent what to pass, how to pass it, what the tool checks, and what the result contains. Nothing necessary for basic invocation is missing.

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% and already describes the config parameter as JSON text, so the baseline is 3. The description adds value by pointing to real file names and emphasizing that the agent must paste the text rather than pass a path or object.

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 verb ('Review') and resource ('MCP client config'), and enumerates the concrete security issues it flags, such as unpinned packages, plaintext secrets, and non-read-only database access. The 'before you trust it' framing and detailed checklist distinguish it from generic config or compliance siblings.

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?

Gives a clear trigger ('before you trust it') and concrete input sources (.mcp.json, claude_desktop_config.json, or equivalent). It does not explicitly mention when not to use it or route to sibling tools like check_config_compliance, so it stops short of full alternative guidance.

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