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

The description discloses the paid nature ('PAID: 500 micro-dollar service credits per successful call'), prerequisites (credits, Authorization header), the preparation step, and that a new requestId is a new billable operation. It also states that cookie values are masked, which is a behavioral detail beyond the annotations (idempotentHint=true, readOnlyHint=false). No contradiction with annotations.

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 tight and front-loaded: purpose, cost, preparation, and recovery each get exactly one clause. No redundant or filler wording. Every sentence contributes actionable information, and the most critical facts (what it does, cost) come first.

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 paid, stateful tool, the description covers all essentials: prerequisites, billing, recovery, and the preparation flow. The output schema exists, so return values are documented. The combination of description, annotations, and schema leaves no critical gap for an agent to call this tool 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?

The schema already provides descriptions for requestId and maxPriceMicroUsd, and setCookies has maxItems=50. The description reiterates the 50-cookie limit but adds no new parameter semantics. With schema coverage at 67%, the baseline of 3 is appropriate; the description does not compensate for the undocumented input object beyond what the schema implies.

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 ('check'), a concrete resource ('Set-Cookie headers'), a scope ('up to 50'), and what is evaluated ('security attributes and prefix rules'). It also mentions masking values, distinguishing it from sibling tools like security_header_audit or security_csp_audit. An agent can clearly tell what this tool does without opening the schema.

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 clear procedural guidance: 'First use agent_utilities_prepare', requires credits and a private Authorization header, and explains recovery and billing. However, it never mentions when to use this tool over sibling audit tools (e.g., security_header_audit) or when not to use it. The agent must infer applicability from the stated purpose, which is less explicit than the ideal.

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