audit_mcp_config

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

With no annotations, the description must carry the full behavioral burden. 'Scan' implies a read-only inspection and the description discloses the detection categories and a specific CVE (2025-59536), which is genuinely useful context. However, it never confirms the operation is non-mutating, says nothing about what happens if a config file is missing, and does not describe what a finding or report looks like.

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?

Two tight sentences: the detection scope with concrete file paths and issue categories comes first, the usage cue second. No filler, no restatement of the tool name.

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?

No output schema and no annotations, but the enumerated issue categories effectively tell the agent what kinds of findings come back, and the file list scopes the behavior. The remaining gap is that the format parameter's consequence (markdown report vs JSON) is never explained, which matters for a tool whose primary product is a report.

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 description coverage is 100% with only two self-documenting parameters (path with default '.', format enum with default markdown), so the baseline is 3. The description adds no parameter-level meaning beyond implying the default path is a project root; it never mentions that output can be JSON or markdown, which is the one parameter choice an agent would benefit from guidance on.

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 ('Scan') and a precisely bounded resource: MCP config files, with the three concrete paths (.claude/settings.json, .cursor/mcp.json, .vscode/mcp.json) enumerated, plus the four issue classes it looks for. This is far more specific than a generic 'audit' sibling like audit_config or audit_config, though it never explicitly contrasts itself with scan_host_config or scan_config_change, which an agent could plausibly confuse it with.

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?

'Use this to verify MCP configurations are safe before use' gives a clear triggering context (pre-adoption verification of MCP configs). It does not name exclusions or point to alternatives such as audit_config for broader scope or remediation_plan once issues are found, so it stops short of full routing guidance.

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