Returns a clear error because this YC company extraction is withdrawn pending a review of source terms, so existing clients get an immediate, actionable answer instead of a failure.
Withdrawn in 0.5.3 pending review of source terms. Returns an error; kept so existing clients get a clear answer.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | YC companies URL e.g. https://www.ycombinator.com/companies?query=mcp | |
| max_length | No |
Changes observed during successful MCP inspections.
v0.3.12Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses behavior the annotations cannot: the tool is withdrawn as of a specific version, is pending a source-terms review, and will always error rather than perform a fetch. This is exactly the kind of non-obvious behavioral fact an agent needs, and it does not conflict with readOnlyHint/openWorldHint.
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Two short sentences, zero filler, and the critical fact (withdrawn, returns error) is front-loaded so the agent sees it first.
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 deprecated stub with no output schema, the description contains what an agent needs to avoid a dead call. The one gap is a pointer to the recommended replacement tool, but nothing required for correct handling is missing.
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 only 50% (url is documented, max_length is not) and the description adds no parameter meaning whatsoever. Normally an inert stub makes params moot, but by the rubric the description does nothing to compensate for the coverage gap.
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 plainly states the tool's current behavior: it is withdrawn and returns an error, so an agent immediately knows this is a non-functional stub rather than a working extractor. It distinguishes itself from the many functional extract_* siblings by declaring non-operation, though it never says what the tool originally extracted (YC company data) beyond what the name and url param imply.
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?
It gives an implicit directive not to use the tool ('Returns an error') and explains the audience it is retained for ('existing clients get a clear answer'). However there is no explicit 'do not call' instruction and no named alternative (e.g. extract_company_landscape) for agents that actually need YC data.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.