web_fetch

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

With no annotations, the description carries the full behavioral burden and does well: it discloses the http/https-only restriction, JSON pretty-printing, the 30-link cap, the max_chars bound, and — importantly — that failures return text prefixed 'error[KEYLESS_...]:' plus a Hint rather than raising. Not covered: redirect policy, JS-rendered pages, rate limits, or how truncation is signalled in the returned text.

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?

One dense paragraph with zero filler, front-loaded with the primary purpose before the scheme restriction, optional-parameter behavior, and failure mode. Every clause adds an actionable fact.

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 values need not be re-explained, yet the description usefully covers the error-return convention that callers must parse. For a fetch tool the remaining gaps are environmental (redirects, JS-rendered content, truncation indicators), which are minor but non-trivial for a web-reading agent.

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 compensate, and it does: url is constrained to http/https, include_links is given real semantics ('up to 30 links found on the page ... to discover follow-up URLs'), and max_chars is bounded. The max_chars range largely restates the schema's minimum/maximum, which keeps this just short of a 5.

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 ('Fetch one http(s) URL') plus the concrete output ('readable main text for reading or citation') and the JSON special case. An agent can immediately tell this apart from its sibling web_search, which discovers URLs rather than retrieving a known one.

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 only implied: 'for reading or citation' and the note that include_links helps 'discover follow-up URLs' hint at the workflow, but the description never says when to choose this over web_search or whether a prior search is required. No exclusions or prerequisites are stated.

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