fetch

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the tool as readOnlyHint=true, and the description reinforces this by framing it as a READ operation. It adds useful behavioral detail beyond the annotations: static pages use plain HTTP, JS-rendered pages require a browser, and render_tier changes the HTTP vs. browser strategy, including that 'http' refuses the upgrade to browser.

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 three sentences and front-loads the core purpose, then gives usage guidance, then explains tier behavior. It is compact and readable, though the render_tier sentence is slightly dense with inline quotes and colons.

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?

Given the comprehensive input schema, the description is sufficiently complete: it names the return formats, covers common web page types, explains rendering tiers, and the annotation confirms read-only safety. It does not detail error behavior or truncation via max_chars, but the schema already documents those parameters, and the absence of an output schema is mitigated by the description's explicit return format.

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 all 10 parameters. The description adds a helpful plain-language explanation of render_tier's options, but it does not add meaning for the other parameters beyond what the schema provides. This meets the baseline for high schema coverage.

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 ('Fetch') and resource ('a webpage') and specifies the return format ('clean markdown/html/text'). It clearly positions itself as the read tool, distinguishing it from sibling tools like session_navigate and download by focusing on reading web content and returning parsed text.

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?

Explicitly says 'Use whenever the agent needs to READ any web page' and lists concrete use cases: blogs, docs, articles, JS-rendered SPAs, and Cloudflare-protected sites. It does not explicitly say when not to use it or name alternatives, but the context is clear enough for an agent to route most read tasks here.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.