web_fetch

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

With no annotations, the description carries the burden and does disclose two non-obvious traits: output is filtered to focus-relevant passages rather than the full page, and the fetched content is untrusted data (a prompt-injection safety signal). It omits rate limits, error behavior, and how session_id is obtained.

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 short sentences, fully front-loaded: action and scope first, safety note second. No filler, every clause 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?

An output schema exists, so return-value detail is not required, and the description covers formats, filtering, and trust level. Remaining gaps are minor: session_id's origin and max_tokens interaction with the filtered output are left implicit.

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 75% and the schema already documents focus, target, and max_tokens ('output cap'). The description reinforces what focus does (passage filtering) but adds no syntax or format detail for target or session_id, so the baseline of 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?

States a specific verb ('Read') and resource ('one page (HTML/PDF/text)') and adds scope ('returning only passages relevant to focus'). It is clearly distinguishable from web_search by implication (read one page vs search), though it never names the sibling or contrasts explicitly.

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?

Usage is implied: give a URL or result id and a focus to get extracted passages. There is no explicit when-to-use vs web_search, nor any statement of prerequisites (e.g. obtaining session_id or a result id from web_search).

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