Return origin, host, and path for a URL. Query and fragment are dropped.
| 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, and it does disclose one key behavioral trait: query and fragment are dropped. It does not, however, explain handling of invalid URLs or the role of the json and zone parameters, which could surprise an agent invoking the 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?
Two short sentences, no filler, and the core behavior is front-loaded. Every phrase ('Return origin, host, and path', 'Query and fragment are dropped') earns its place.
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 description is incomplete for a tool with four parameters and no output schema. It explains what happens to the 'url' input but does not describe how 'host', 'json', or 'zone' are used or expected, and it provides no return type details beyond the three components. An agent cannot confidently determine whether those parameters are optional, ignored, or alternative modes.
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%, so the baseline is 3. The description adds minor value by clarifying that 'url' is the input and that its query/fragment are stripped, but it introduces ambiguity by using 'host' as an output term when 'host' is also an input parameter. It adds no meaning for 'json' or 'zone' beyond the schema.
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 specific verb ('Return') and resource ('URL') and details the exact outputs (origin, host, path). It also notes the dropped query/fragment, which further defines scope. However, it does not explicitly differentiate this from sibling tools such as validate-json or punycode-ok, so it stops short of a 5.
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?
No guidance is given on when to choose normalize-url over its siblings. There is no mention of alternatives, conditions, or exclusions, leaving the agent to infer the intended context from the name alone.
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.
Most tools have distinct outputs, but there are overlapping clusters: citation and normalize-url both return host information, timezone/utc-time/iana-zones all revolve around time, and domain-shape/punycode-ok both target hostnames. An agent would need to read descriptions carefully to avoid picking the wrong one.
Naming style is inconsistent: some names are verbs (normalize-url, validate-json, inspect-robots), some are nouns (citation, compatibility, timezone), and some are quirky compounds (punycode-ok, iana-zones). The consistent lowercase/hyphen formatting is the only pattern.
Eleven tools is not an unreasonable count by itself, but the server is named for punycode host checking while many tools are unrelated URL, time, and JSON utilities. The set feels padded rather than deliberately scoped.
The tool surface has no coherent domain to be complete against: a punycode host checker would need at least IDN conversion or comparison, while the URL/time/JSON utilities appear as unrelated extras. Significant coverage gaps would likely force agents to combine or externalize work.