audit_delivery

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

No annotations are provided, and the description does not disclose any behavioral aspects such as side effects, read-only nature, or rate limits. It simply says 'Audit' without clarifying whether it modifies anything or is purely observational.

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, concise sentence with no redundant or filler content. It efficiently lists the key audit areas without unnecessary elaboration.

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?

The description provides specific details about what the audit covers, which is sufficient for a simple one-input tool. However, it does not mention what the output looks like or any edge cases, but given the absence of an output schema, the provided scope is mostly adequate.

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?

The schema has a single 'html' parameter with 100% coverage, and the description mentions 'page HTML string', which adds minimal clarity. Since coverage is high, the baseline is 3, and the description does not significantly exceed that baseline.

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 audits an HTML string for delivery performance, listing specific checks (unsized images, lazy-loaded first image, render-blocking head scripts, inline @font-face without font-display). It distinguishes from sibling audit tools by focusing on delivery-specific issues.

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 does not provide any guidance on when to use this tool versus other audit tools (e.g., audit_surface or audit_findability). There is no explicit scenario or condition suggesting when delivery auditing is appropriate.

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