web_fetch$0.005 per call — Fetch a public URL and return status, final URL, title, cleaned text (scripts/styles stripped, truncated) and the top 20 absolute links. Useful when an agent itself cannot reach the open web.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Target URL; protocol optional (https:// added if missing) | |
| maxChars | No | Max characters of cleaned text (default 4000) |
Changes observed during successful MCP inspections.
Input schema / properties / maxCharsAdded value: +{
+ "description": "Max characters of cleaned text (default 4000)",
+ "type": "number"
+}Input schema / properties / qRemoved value: -{
- "description": "JSON or key=value input for the tool",
- "type": "string"
-}Input schema / properties / urlAdded value: +{
+ "description": "Target URL; protocol optional (https:// added if missing)",
+ "type": "string"
+}Input schema / requiredAdded value: +[
+ "url"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full burden, and it does well: it discloses per-call cost ($0.005), the exact return shape, that scripts/styles are stripped, and that text is truncated. 'Public URL' implicitly rules out authenticated/private content. It still omits rate limits, auth requirements, and whether JS-rendered pages are handled.
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 sentences: cost first, then the operation and payload, then a single routing hint. Every clause earns its place and nothing is repeated from the schema.
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, the description compensates well by enumerating the returned fields including the top-20 link cap. It is nearly complete for a simple fetch tool; only edge behavior such as timeout/error handling and JS-rendering support is unstated.
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 both url and maxChars are already documented with defaults and protocol behavior. The description's mention of truncated cleaned text loosely ties to maxChars but adds no syntax or constraints beyond the schema, making 3 the correct baseline.
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 a specific verb+resource ('Fetch a public URL') and enumerates the return payload (status, final URL, title, cleaned text, top 20 links), which is unusually precise for a fetch tool. It does not differentiate itself from plausible siblings like web_brief or free_url_check, so it stops short of 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?
'Useful when an agent itself cannot reach the open web' gives one triggering condition, which is a real usage hint rather than none. However, it never says when to prefer this over web_brief (presumably the summarization sibling) or free_url_check, so the agent must infer the routing.
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.