Show how this request is classified. No identifiers are retained.
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | HTTPS URL to normalize or cite | |
| host | No | Public hostname | |
| json | No | JSON text to validate; discarded after the check | |
| zone | No | IANA timezone name |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of explaining side effects, output, and data handling. It only promises that identifiers are not retained, leaving the actual behavior and potential errors undisclosed.
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 text is brief and front-loaded, with no redundant wording. However, the brevity omits essential context about the tool's purpose, making it under-specified rather than efficiently concise.
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 no output schema, no required parameters, and no annotations, and the description does not explain the classification result, categories, or parameter usage. It is not complete enough for an agent to know when or how to invoke it 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?
Each parameter has a short schema description, but those descriptions are generic and seem copied from other tools (URL normalize/cite, JSON validate, timezone). The description does not explain how url, host, json, and zone relate to 'classification' or how they should be populated for this tool.
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 it will 'show how this request is classified' but does not define what classification means or what resource is being classified. It does not differentiate this tool from the sibling tools, several of which also operate on URLs, JSON, or timezones.
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 instead of the siblings. The only additional note, 'No identifiers are retained,' is a privacy statement, not a usage criterion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several URL-centered tools (citation, normalize-url, domain-shape) and time tools (timezone, utc-time) overlap in input type and could be confused, though their output purposes are mostly distinct. The vague 'compatibility' tool lacks a clear boundary, and 'lang-hi' seems unrelated to the rest.
All names use lowercase kebab-case, which gives a consistent visual pattern, but the grammatical style is mixed: some are verbs (normalize-url, validate-json), some nouns (citation, timezone), and some are opaque (compatibility, lang-hi). It is readable but not a clean verb_noun convention.
With 11 tools, the count is within a reasonable range for a utility server and not bloated. However, a few tools feel like one-offs or constants (lang-hi, iana-zones), so the set does not feel perfectly curated.
The tool surface is a grab bag of URL, HTTP status, robots, time, JSON, and language utilities, so there is no coherent domain to complete. For a web/URL toolkit, obvious operations like header inspection, content fetch, or DNS/WHOIS are missing; for a language server, only a tag constant is present.