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

The description discloses behavioral traits beyond the annotations. It explicitly says 'READ-ONLY' and 'informational only, not a formal audit or warranty,' unlike the readOnlyHint=false (which might suggest it could write). It also states it 'always names what it did NOT check' and how it handles consent and asset restrictions. This gives the agent full awareness of the tool's scope and limits.

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 concise yet information-dense. It front-loads the key facts (consent-gated, READ-ONLY, informational) and includes input format and cost in a compact structure. Every sentence adds value: purpose, constraints, exclusion criteria, and input specification. No filler.

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?

Given the tool's complexity (external audit, consent requirements, restrictions), the description is comprehensive. It covers the tool's purpose, what it checks, what it refuses, the consent flow, and the expected input. Even though there's no output schema, the description clarifies the report's nature. It is complete for an agent to decide and invoke 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 100% (the schema already documents asset and consent_id with detailed descriptions). The description adds meaningful context: asset must match the consented host, IP literals are refused, and consent_id must be bound to the exact asset and expires in 24h. This goes beyond the schema's basic wording, providing critical operational semantics.

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 the tool's purpose: a 'Consent-gated, READ-ONLY external posture report' that 'observes over HTTPS what the internet already sees: security headers, software banners, and exposed /.env //.git/admin surfaces.' It uses a specific verb (observes) and resource (external posture), and distinguishes from siblings like 'independent-ai-third-party-audit' by being informational and not a formal audit.

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 provides clear context for when to use it: requires consent, works on externally exposed hosts, and names what it does NOT check. It also states 'internal targets refused' and 'No consent → no probe.' While it doesn't explicitly name alternatives, the differentiation from formal audits is implied. A brief note on when not to use (e.g., for internal assets) would make it perfect, but it's nearly explicit.

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