web_metadata_discoveryProbe a bounded set of standardized and conventional metadata paths on an authorized web origin to uncover exposed files and config clues.
Probe a bounded set of standardized and conventional metadata paths on an authorized origin.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| paths | No |
| Name | Required | Description | Default |
|---|---|---|---|
| origin | Yes | ||
| results | Yes | ||
| found_count | Yes |
Changes observed during successful MCP inspections.
v2.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds two useful behavioral facts — that the probe is 'bounded' (matching maxItems 20) and limited to an 'authorized origin' — but says nothing about concurrency, request volume, or what artifacts are collected. With annotations carrying the safety story, a 3 is appropriate.
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?
A single front-loaded sentence with no filler, and the scope constraints come early. It is efficient, though arguably too terse for a tool embedded in such a dense sibling set.
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?
An output schema exists, so return values need not be explained, and annotations cover safety. But with two parameters at 0% schema coverage and dozens of overlapping discovery siblings, the description is not complete enough to let an agent choose and configure this tool 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?
Schema description coverage is 0%, so the description must compensate for both parameters. It gestures at 'metadata paths' (loosely mapping to the paths array) but never explains url vs. paths, the 20-item cap, uniqueness, or the default behavior when paths is omitted. The heavy lifting is left to an undocumented 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 gives a verb ('Probe'), a resource ('standardized and conventional metadata paths'), and a scope ('bounded', 'authorized origin'), so the basic operation is inferable. However, 'metadata paths' is ambiguous — it does not distinguish this tool from siblings like robots_txt_analysis, sitemap_analysis, security_txt_analysis, or openapi_discovery, which all probe well-known metadata locations. The agent cannot tell what this tool covers that the specific siblings do not.
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 statement of when to use this tool versus the many adjacent discovery siblings, and no exclusions. The phrase 'on an authorized origin' hints at an authorization prerequisite but is not framed as guidance. Nothing routes the agent between this and the overlapping single-purpose probes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.