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

With no annotations, the description carries the full behavioral burden and does disclose the two things an agent worries about most here: no payment / no x402 challenge, and an HTTP equivalent endpoint. It implies static read-only content via 'published criteria' but does not explicitly state read-only, idempotent, or side-effect-free behavior, nor anything about response size or pagination.

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?

Front-loaded with the purpose, followed by the content inventory, the read-before-paying instruction, the free-access note, and the HTTP equivalent. The dense enumeration of registers and factor ranges is longer than typical but each item is informative rather than 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?

With zero parameters and no output schema, the description must convey what comes back, and it does so by enumerating the criteria sections in detail. The main remaining ambiguity is how large the payload is and whether it should be cached across audit calls.

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 tool takes no parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The HTTP equivalent line usefully maps the parameterless invocation to a concrete GET endpoint.

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?

Names a specific resource (the published criteria for the Context Audit service, context-composition/v1) and enumerates its sections: record formats/adapters, two-axis composition classes, metric register M01-M15, factors F-1 to F-12, typography rule, and corpus identity. An agent can tell this is a static documentation/spec retrieval tool rather than the paid audit itself, though the sibling context_audit_audit and context_audit_precheck are never named 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?

Gives a clear use condition: 'Read these before paying - every report is reproducible from them', which tells the agent to consult this prior to the paid audit call. It also removes a common blocker by stating no payment is required. It stops short of explicit when-not guidance or naming the alternative tools to invoke afterward.

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