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

Goes well past the annotations: it discloses the verdict taxonomy (PASS/REVIEW/BLOCK/UNKNOWN), that UNKNOWN is never upgraded to PASS, the CENSUS-AUDIT/1 text plus valid_until_epoch and exit_code (1 on any BLOCK), credit cost, rate limits, and the security caveat. None of this is derivable from readOnlyHint/destructiveHint/openWorldHint.

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 verb, resource, and supported formats, then stacks the return shape, cost, and caveats. It is a dense paragraph rather than a list, so the cost and safety caveats can be skimmed past, but essentially every sentence carries non-redundant information.

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 does the work of describing return values (per-entry verdict, CENSUS-AUDIT/1 text, valid_until_epoch, exit_code) and adds cost/rate-limit context, so an agent can call it correctly. The residual gap is policy selection semantics for the three enum values.

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?

At 60% schema coverage the description adds real meaning for `config` (accepted shapes, resolution of url/npx/uvx entries, the env/headers stripping advice) and indirectly for `previous_tools_digests`. But `policy_id` is only alluded to as 'a built-in policy' with no explanation of what builtin:baseline vs first-party vs strict actually enforce, and `format` is never tied to the json/toml enum.

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 concrete verb-plus-resource ('Audit a whole MCP client config in one call') and enumerates the exact file formats accepted (.mcp.json, claude_desktop_config.json, .cursor/mcp.json, .vscode/mcp.json, Codex config.toml). The phrase 'whole config in one call' implicitly separates it from the single-entry lookup siblings, so an agent can pick it without opening a 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?

Gives clear conditions and exclusions ('Not a malware scan; PASS is not a sandbox'), a prerequisite ('Strip env/headers before sending'), and hard limits (1 credit per config per UTC day; keyless callers limited to one config of ≤25 entries per IP per day). It never names a concrete alternative sibling tool for single-server checks, which is the one routing gap.

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