web_fetch

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

Adds substantial context beyond annotations: writes to disk (consistent with readOnlyHint=false), rejects executable/archive/document extensions and non-text content types, strips scripts/forms/iframes/event handlers/unsafe links, and blocks private/loopback addresses. The user-confirmation requirement is a behavioral constraint the annotations do not encode.

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 tight sentences covering purpose, return contract, and rejection/sanitisation rules, with the most important constraint (user confirmation) placed first. No filler or restatement of the tool name.

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?

Strong coverage of safety behavior and return handling, and an output schema exists so return values needn't be spelled out. The gap is the missing explanation of the output_dir parameter and how the destination filename is derived.

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 0%, so the description must explain both parameters, but it never mentions output_dir or its default 'fetched', nor where the markdown file lands. The URL parameter is only implied by 'Download a web page', with no format or validation details.

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 concrete verb chain (download a web page, sanitise it, save it as a local markdown file) and specifies the return contract: a file path, not page content. This is clearly distinguishable from siblings like http_request or read_text_file, since its output is a persisted markdown artifact.

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 requires 'explicit user confirmation' before use, which is a real gating condition, and tells the agent the next step ('read the file to consume it'). It stops short of naming an alternative such as http_request for non-HTML APIs or raw responses, so the when-not case is left to inference.

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