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

With annotations = None, the description carries the full disclosure burden. It adds one genuine tool-level trait, 'No identifiers are retained', which is a meaningful privacy statement, though it partly echoes the schema's per-parameter 'discarded after the check' notes. It does not disclose return format, whether classification is local and synchronous, error behavior, or external-call 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?

Two sentences with zero filler; the purpose is front-loaded and the privacy note follows. Each sentence earns its place. The terseness borders on under-specification for an 8-parameter router, but judged purely as conciseness and structure, it is efficient and well-ordered.

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 tool has 8 heterogeneous parameters, no annotations, and no output schema, yet the description explains neither the classification output, the input contract (e.g., exactly one argument expected), nor how it relates to the 27 siblings. The richly described schema parameters only partially compensate for the missing tool-level context.

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 coverage is high: all 8 parameters (ref, url, city, feed, host, json, path, search) have individual descriptions, so the baseline is 3. The tool description itself adds no parameter-level meaning and never clarifies whether the parameters are mutually exclusive single inputs rather than combinable fields, which is a notable gap for a classifier.

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 resource ('Show how this request is classified'), so it is not a tautology, but 'classified' is left abstract — no classification taxonomy or output category space is named. Among 27 shape-check siblings, nothing in the description differentiates this tool as the routing/dispatch entry point except the generic phrasing.

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 offers no guidance on when to use this tool versus alternatives like domain-shape, validate-json, or normalize-url. Neither conditions for use, exclusions, nor the intended 'call this first to determine the input category' workflow are stated, so an agent must infer usage from the 8 heterogeneous parameters.

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