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

The description discloses several behavioral traits beyond annotations: it is not a malware scan, PASS is not a sandbox, UNKNOWN is never upgraded to PASS, it costs credits, and keyless callers have rate limits. It also advises stripping env/headers before sending, which is critical for safe invocation. Annotations are minimal (readOnlyHint false, etc.), so the description carries the full transparency burden and does so thoroughly.

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 a single dense paragraph that front-loads the purpose and packs in essential details (verdicts, exit codes, costs, security). Every sentence adds value, though it is longer than average; it remains efficient given the tool's complexity.

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 complex tool with 5 parameters and no output schema, the description covers the core return format (verdicts, CENSUS-AUDIT/1 text, valid_until_epoch, exit_code) and includes security and cost constraints. It omits details on policy_id and format parameters, but the schema covers some and the description provides enough for a competent agent to call it correctly.

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 60%, with descriptions for config, strict, and previous_tools_digests. The description adds context about config formats (object/string/array, Codex config.toml) and the overall audit behavior, but it does not explain format or policy_id, which lack schema descriptions. It partially compensates but leaves gaps.

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?

The description clearly states a specific action: auditing a whole MCP client config, listing the exact config file types and describing the resolution and verdict behavior. It distinguishes itself from siblings like census_lookup by emphasizing whole-config auditing, so an agent can tell it apart without ambiguity.

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?

It provides strong context on when to use it (whole-config audit, resolving entries) and implicitly contrasts with per-entry tools, but it does not explicitly name an alternative or state when not to use it. The cost and rate-limit details further clarify appropriate usage.

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