ContextFetch research (evidence pack)

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

Annotations only cover read-only and open-world, yet the description discloses a great deal more: concurrent execution, URL dedupe, cross-encoder ranking, the exact return format (numbered [n] sources with query-pruned verbatim passages, no generated text), and the billing model (1 credit per sub-query). The default sub-query derivation rules are spelled out, so the agent can predict behavior when it omits the parameter.

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?

Purpose is front-loaded in the opening clause and every sentence carries information. The parenthetical explaining default sub-query derivation is long and reads almost like spec text, but it is genuinely useful rather than filler, so it slightly dilutes an otherwise tight structure.

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?

There is no output schema, and the description fully compensates by describing the return shape (Markdown evidence pack with numbered sources and verbatim passages) and the cost model. For a 3-parameter, read-only aggregation tool, an agent has everything needed to call it correctly and to anticipate the response.

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%, so the baseline is 3; the schema already documents all three parameters including ranges and defaults. The description does add genuine meaning for sub_queries ('distinct angles', plus the fallback derivation algorithm), but says nothing about num_results_per_query beyond what the schema supplies.

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 precise verb and resource ('Research a question in one call') plus the concrete artifact returned (a Markdown evidence pack), with operational mechanics (5 concurrent searches, URL dedupe, cross-encoder ranking) that make it hard to confuse with a plain search. However, it never names or contrasts any sibling tool such as contextfetch_deep_research or contextfetch_search, leaving the differentiation implicit rather than stated.

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?

Gives real context: 'Pass your own sub_queries (distinct angles on the question) for better coverage' tells the agent how to get the best result, and the credit cost per sub-query informs the cost/coverage trade-off. It stops short of explicit when-to-use/when-not guidance or naming the alternative tools an agent should pick instead.

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