security-preflight__security_preflight

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

With no annotations provided, the description must carry the full behavioral burden. It discloses genuinely useful traits: static-only analysis, no deployed endpoint is fetched, a signed receipt is produced, and importing into a market profile is separate and explicit. But it says nothing about idempotency, side effects, whether the receipt is persisted, or what the optional policy argument changes about behavior.

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?

Three compact sentences, front-loaded with the scope bracket and the core action. Pricing and import caveats are lower-value but short; the description is appropriately sized with no padding.

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?

There is no output schema, so the description must explain return values, and it only says 'a signed receipt' without format, fields or how to retrieve it later. For a 7-parameter, nested-object tool with zero annotation and zero schema coverage, key gaps remain around the policy override and the optional request_id/payment_ref parameters.

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 0%, so the description must compensate for seven parameters and it does not. manifest, sample_inputs and subject_profile_sha256 are at least inferable from the 'static manifest, source and text' framing, but policy, request_id, payment_ref and agent_id receive no explanation at all, and the role of policy in altering the checks is entirely undocumented.

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 action: run a static Security Preflight over manifest, source and text material and return a signed receipt. It distinguishes itself from its closest sibling security-preflight__scan_source by framing itself as a bundled preflight rather than a single-source scan, though it never names or contrasts the sibling explicitly.

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?

Usage is only implied by the bracketed scope ('static manifest, source and text security checks'). There is no explicit when-to-use guidance, no statement of when to prefer scan_source or screen_injection instead, and no prerequisites stated.

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