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

With no annotations, the description carries the full burden. It adds one useful behavioral note ('No identifiers are retained'), but it does not say whether the tool performs external calls, whether it is read-only, what side effects occur, or how input is actually processed. This is insufficient for an unannotated tool.

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 short and front-loaded with the main action, followed by a relevant privacy note. There is no filler, though the brevity contributes to its under-specification.

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?

A tool with nine optional parameters, no output schema, and many closely related sibling tools needs a more complete description. The agent is left to guess what classification result is returned, how to choose among parameters, and how this relates to the alternative tools.

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 input schema provides 100% description coverage, with each parameter having a meaningful explanation (e.g., 'discarded after the shape check', 'HTTPS URL to normalize or cite'). The tool description itself adds no parameter semantics, so the baseline 3 applies.

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 verb and object ('Show how this request is classified') but never defines what classification means or what the result looks like. It does not distinguish this tool from specialized siblings like validate-json, domain-shape, or normalize-url, so an agent cannot tell what unique role 'compatibility' plays.

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?

There is no guidance about when to use this tool versus the many sibling shape-checking tools. It does not explain whether this is a router to other tools, a pre-check, or a standalone classifier, and it gives no conditions, exclusions, or example triggers.

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