Audit MCP configuration

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description reinforces this while adding genuinely new information: 'launches nothing' tells the agent that pipe-to-shell commands and npx/uvx packages are inspected but never executed, which is a meaningful safety guarantee beyond the annotations. It stops short of describing finding severity, output volume, or how results are ordered.

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?

Purpose is front-loaded in the first clause, followed by a compact checklist of detection categories and a one-clause safety note. The enumeration is long but every item is load-bearing for distinguishing this tool's coverage; no filler sentences.

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?

For a zero-required-parameter, read-only scan with no output schema, the description supplies enough to call it correctly: it states the input domain (config), the static/non-executing nature, and the categories of findings an agent should expect back. It does not sketch the return shape, but the finding enumeration is a reasonable proxy.

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?

Single optional parameter with 100% schema description coverage, so the schema already documents project_dir and its default. The description adds no further meaning about path resolution, relative vs absolute paths, or multi-scope behavior, so baseline 3 applies.

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?

Specific verb (audit) plus a precisely scoped resource (MCP server configuration) that is explicitly static and config-file-only. The enumeration of seven detection categories (plaintext secrets, plain-HTTP remotes, unpinned npx/uvx, privileged Docker, pipe-to-shell, duplicate names) cleanly separates it from audit_server_tools, check_supply_chain, and adversarial_test without the agent needing to open any schema.

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 scope of the check implies when the tool applies, and 'Static audit' plus 'launches nothing' signals a pre-execution/configuration-review context. However, no sibling is named and there is no explicit when-to-use or when-not-to-use statement relative to audit_server_tools, check_supply_chain, or adversarial_test, so the agent must infer routing.

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