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

Annotations already declare readOnlyHint=false, openWorldHint=true, destructiveHint=false. The description adds valuable behavioral context: it is ownership-gated, requires attest_owner:true, does not probe hosts itself, and costs 4 MESH/call. This goes beyond the annotations by clarifying the non-probing, query-generation-only behavior and the ownership attestation requirement.

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 tool's identity and purpose, then lists inputs, outputs, and a key exclusion. It's efficient with no wasted words, though the parenthetical '(4 MESH/call, a tool · audit)' is slightly noisy and could be cleaner. Overall it earns its place.

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 tool with one generic input parameter and no output schema, the description does a good job explaining what to provide and what to expect. It covers the ownership gate, the input categories, the output categories, and the non-probing behavior. It doesn't specify the exact output format or query syntax, but for a query-kit generator that's a minor gap given the description's clarity.

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% for the single 'input' parameter, but the schema description is generic ('Capability-specific payload, e.g. agent-brain...') and doesn't describe the exposure-dork-kit payload structure. The tool description partially compensates by listing expected inputs (domains, GitHub org, named assets, attest_owner:true), but it doesn't specify the exact JSON shape or field names. Baseline 3 is appropriate since the schema covers the parameter but the description adds some semantic value.

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 states a specific verb ('Feed it domains, a GitHub org, and named assets...') and resource ('returns categorized ready-to-run exposure-search queries'), and clearly distinguishes it from a host-probing tool by saying 'It does not probe hosts itself — query kit only.' This is a clear, specific purpose that differentiates it from siblings like mesh-audit-external-posture or browser-agent-101.

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 description gives explicit input requirements ('domains, a GitHub org, and named assets you own plus attest_owner:true') and states the output ('categorized ready-to-run exposure-search queries'). It implies this is for ownership-gated self-audit, which tells the agent when to use it (self-audit with owned assets) versus alternatives. It doesn't explicitly name sibling alternatives or exclusions, but the ownership-gating and 'query kit only' scope provide clear context.

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