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?
No annotations are provided, so the description carries the full behavioral burden. The 'No identifiers are retained' sentence is a useful privacy disclosure and aligns with the json parameter's 'discarded after the check', but the description does not say whether the tool makes external calls, what the classification result looks like, or whether any state changes occur.
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 short sentences with no filler; the purpose statement is front-loaded and the privacy guarantee earns its place. There is zero wasted wording.
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 tool with four heterogeneous optional parameters, no output schema, and no annotations, this description is insufficient. It does not state what is returned, how the parameters combine or conflict, what the classification categories are, or why a caller would prefer it over the sibling 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?
Schema description coverage is 100%: url, host, json, and zone all have their own descriptions. The tool description adds no meaning about how these parameters relate to the classification and never mentions them, 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 has a verb ('Show') and a high-level subject ('how this request is classified'), so it is more than a restatement of the tool name. However, it never defines what 'classified' returns or what 'compatibility' means, and it names no parameters or output, leaving the purpose vague and indistinguishable from siblings like citation and domain-shape.
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 invoke this tool versus the sibling tools. The description mentions no conditions, prerequisites, or exclusions, so an agent must guess from the schema and sibling names which tool fits the task.
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.
json-ok and validate-json are effectively duplicate JSON validity checks, and several URL/HTTP tools (citation, normalize-url, domain-shape) have overlapping hostname/status concerns. compatibility is too vague to distinguish reliably from the other HTTP-related tools.
The names are all lowercase hyphenated, but they mix noun phrases (citation, timezone), imperative verbs (normalize-url, validate-json), and adjective constructions (json-ok). There is no consistent verb_noun or resource_action pattern, and the same JSON operation is called two different names.
Eleven tools is not inherently too large, but the set is not tightly scoped to the apparent 'JSON validity' purpose and bundles URL, robots, HTTP, and time utilities. The duplicate JSON validation tools also make the count feel padded rather than earning their places.
There are useful clusters for URL inspection, HTTP status, time, and JSON validity, but no clear workflow connects them and compatibility remains unexplained. Within a broad safe-web/utility interpretation the basics are present, yet obvious helpers such as header inspection or a single unified JSON validator are missing.