ContextFetch extractive answer

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

Annotations only cover readOnlyHint and openWorldHint, but the description adds the extraction mechanism (cross-encoder scoring over every passage of top pages), the output contract ([n] citations back to sources), the reliability caveat, and the billing behavior ('Costs 1 credit'). That is substantive context beyond what the structured fields provide.

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 sentences, front-loaded with the defining trait (verbatim, never generated) before mechanism, caveat, and cost. The middle pipeline sentence is dense but earns its place by explaining result quality; nothing is redundant padding.

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, the description compensates by describing the return shape (best passages plus [n] citations) and the credit cost. For a two-parameter read tool whose safety profile is covered by annotations, nothing an agent needs to select or call it is missing.

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 100% and both parameters are already documented, so the baseline is 3. 'Top pages' and 'every passage of the top pages' loosely maps num_results to pages searched, but adds no syntax or semantics beyond the schema's own 'Pages searched for passages (1-10, default 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+resource: 'Answer a question with passages quoted verbatim from the web, never generated.' The 'never generated' clause distinguishes it from a generative research tool and from contextfetch_search, which the passage-scoring description implies returns pages rather than extracted quotes. An agent can pick this out from siblings without opening a schema.

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?

'Use it for quick factual lookups; the quotes may not fully answer an open-ended question' gives a positive trigger and a soft exclusion that steers open-ended work elsewhere. It falls short of naming the alternative sibling (e.g. contextfetch_research / deep_research) explicitly, so the routing is implied rather than stated.

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