Audit MCP tool definitions

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

Beyond readOnlyHint=true and openWorldHint=true, the description discloses that scanning launches server processes or opens HTTP connections, that only initialize and tools/list are sent, and that no scanned tool is ever invoked. This is exactly the extra operational context annotations cannot carry.

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-loads the action and the threat list, then closes with the key safety guarantee. The parenthetical threat enumeration is dense but each item earns its keeping; two sentences, no filler.

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?

With no output schema, the description should ideally hint at what the audit returns (findings, severity, report shape). It covers invocation behavior thoroughly, but the result format is left unspecified for a tool whose output is the whole point.

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 only 50%, and the description adds nothing about the servers list format, project_dir, or timeout beyond what the schema already says. The confirm_launch semantics it implies (requires user consent) are already documented in the schema, so compensation for the coverage gap is marginal.

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 specific verbs and resource: connects to MCP servers, lists tools, and checks names/descriptions/schemas for poisoning, shadowing, and rug pulls. The enumerated threat categories make it clearly distinct from siblings like audit_mcp_config or analyze_tool_definitions.

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?

Provides context (scan servers for poisoning/rug pulls) and a hard behavioral rule (never calls the scanned tools), which implies when to reach for it. However, it never explicitly contrasts with the overlapping siblings analyze_tool_definitions or audit_mcp_config, so the agent must infer which audit tool applies.

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