web_fetch

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

Beyond the annotations (readOnly/idempotent/openWorld/no-destructive), the description discloses substantive behavior: no JS execution, no cookie handling, no local-network access, bounded output, and that retrieved content is untrusted. These are exactly the constraints an agent needs to avoid misusing the tool.

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 with the core action front-loaded and constraints following in priority order. The trailing version/permissions footer '[v1.0.0; permissions: none]' is minor metadata that slightly dilutes an otherwise efficient block.

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 a rich annotation set, a fully covered schema and an output schema covering the return shape, the description supplies all remaining context an agent needs (trust warning, retrieval limitations, output bound) to invoke it correctly.

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% and an output schema exists, so both parameters and return format are already documented. The word 'bounded' loosely gestures at maxChars, but the description adds no parameter syntax or format detail beyond the schema, so 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?

The description uses a specific verb ('Fetch') on a specific resource ('public HTTP(S) page, JSON or text document') and names the return shape ('bounded readable text, title and links'). The distinction from the web_search sibling is implicit (direct retrieval vs discovery) rather than stated, so it is clear but not explicitly differentiated.

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 states clear when-not conditions: 'No browser JavaScript, cookies or local-network access,' telling the agent this fails on JS-rendered pages and private hosts. It does not name the alternative tool (e.g. web_search for discovery or a Safari tool for JS pages), so routing guidance is implied rather than explicit.

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