Fetch a public robots.txt and return group counts only.
| 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 behavioral burden. It does disclose the key output limitation (counts, not full content) and that the resource is public, but it is silent on failure behavior, what happens when robots.txt is missing, and how 'group counts' are defined.
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 a single, front-loaded sentence with no filler. 'Return group counts only' is a concrete, high-value qualifier, and nothing could be trimmed without losing meaning.
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?
With no output schema and no annotations, the agent cannot tell what the returned 'group counts' look like, how to construct the URL/host input, or what the unrelated optional fields do. For a network-fetch tool that must identify a target host, the description is not complete enough to invoke confidently.
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?
Although schema description coverage is 100%, the property descriptions conflict with the tool's stated purpose: 'json: JSON text to validate' and 'zone: IANA timezone name' have no apparent connection to robots.txt group counts, and 'url: HTTPS URL to normalize or cite' does not explain how to form the robots.txt request. The description adds no parameter guidance, and all parameters being optional makes it harder to know what must be supplied.
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 names a specific verb ('Fetch'), a specific resource ('a public robots.txt'), and a precise output scope ('return group counts only'). This makes the tool's role clear and distinguishes it from a generic URL or text processing tool.
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 phrase 'group counts only' implies the intended use case: when an agent needs robots.txt group statistics rather than full content. However, there is no explicit when-to-use/when-not-to-use guidance, no alternatives named, and no mention of prerequisites such as a valid public URL or hostname.
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 tools overlap around URL and request inspection: citation and normalize-url both return host/scheme, and status-catalog overlaps with citation's HTTP status output. The vague compatibility tool compounds the problem, though the time and format-validation tools are clearly distinct.
All names use lowercase kebab-case, but the set mixes imperative verb-noun names (inspect-robots, normalize-url, validate-json) with noun-only or noun-noun names (citation, compatibility, timezone, ulid-shape). This is readable but not a consistent pattern.
Eleven tools is within a reasonable range and each has a separable utility. The count itself is fine, but the server appears to have drifted from the 'ULID shape check' purpose into a general web/time/format utility bag.
As a privacy-focused inspection toolkit, it covers URL, domain, robots, time, status codes, ULID, and JSON shape checks. However, there are notable gaps such as missing common format validators (UUID, email), no URL encoding/decoding, and the compatibility tool feels like an unexplained dead end.