web_fetch

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: a helper model processes the page and returns only the answer when `question` is set, and otherwise cleaned (and capped) page text is returned. It omits auth requirements, rate limits, and failure modes such as dynamic or blocked pages.

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?

Three short sentences, front-loaded with the core action, then the two modes, then the cost rationale. No filler; every sentence earns its place.

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 and no annotations, the description does the work of explaining what each mode returns, which is the key unknown for a fetch tool. It stops short of covering error/dynamic-content behavior and what the text cap actually is, but the essentials for calling it correctly are present.

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 coverage is 100%, so the baseline is 3, but the description goes further by explaining the mechanical consequence of supplying `question`: a downstream model reads the full page and returns just the answer, versus raw cleaned text without it. This adds real meaning beyond the schema's brief descriptions.

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 and resource ('Read a web page'), and the two operating modes are spelled out. It does not explicitly name or contrast with the sibling web_search, so an agent still has to infer the fetch-vs-search distinction, but the core purpose is unambiguous.

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 clear mode-selection guidance for the `question` parameter ('far cheaper than loading the page into Claude'), which is effectively a cost-based routing hint. However, it never states when to choose this tool over siblings like web_search or ask_agent, so tool-level usage guidance is only implied.

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