web_extractFetch a web page and extract its main content as Markdown, including title, author, published date, canonical URL, and outbound links.
Fetch one web page and extract its main content as markdown with title, author, published date, canonical URL and outbound links.
| Name | Required | Description | Default |
|---|---|---|---|
| request | Yes | One page to fetch, with the caller's bounds. |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v2.5.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds useful output context (markdown extraction plus specific extracted fields) but says nothing about size limits (max_bytes), timeouts, rate limits, or failure behavior.
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 verb first and no wasted words. The extracted-field list earns its place by telling the caller what the markdown payload contains.
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?
Output schema exists so return values need not be explained, and annotations cover safety, making the description adequate. The material gap is the absence of any disambiguation from the very similar web_fetch sibling, which is exactly what the description should carry.
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 schema already documents url, job_ref, max_bytes, timeout_s and accepted_types. The description adds no parameter-level meaning beyond that, 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?
States specific verbs (fetch, extract) and resource (one web page), plus the output shape (markdown with title, author, published date, canonical URL, outbound links). However, it never differentiates from the obvious sibling web_fetch, so an agent cannot tell the two apart from the description alone.
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 when-to-use guidance and no mention of the near-identical sibling web_fetch. The description implies use ('fetch one web page') but gives no condition for choosing this tool over alternatives or when it should not be used.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.