Research on the web

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint and destructiveHint=false, so the safety profile is fully covered. The description adds genuine context beyond that: the exact shape of the reply and the fact that output length is bounded by max_tokens. It does not disclose latency, cost, or what happens when the web yields nothing useful.

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 sentences, zero filler, and the core action is front-loaded ahead of the return description. The enumerated return fields earn their space because there is no output schema to carry them.

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 correctly shoulders the burden of describing the return value (answer, confidence, findings, sources, gaps) and the size cap. Safety is covered by annotations and every parameter is documented in the schema. What remains missing is the sibling differentiation and any note on freshness or failure behavior.

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 question, goal, format and max_tokens are already documented, including the notable 'never put secrets here' warning on goal. The description only restates the max_tokens ceiling, adding no syntax or format nuance beyond the schema; 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?

States a specific verb (research) and resource (a question on the web) plus the required framing (a stated goal), and goes further by naming what comes back: answer, confidence, verbatim-quote findings, sources, gaps. It never distinguishes itself from the sibling tools (web_lookup, web_read, web_page, web_investigate), so the agent must infer which of the family to call.

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 by 'for a stated goal' — a goal-bearing research call rather than a raw fetch — but there is no explicit when-to-use, when-not-to-use, or named alternative among the four sibling web tools. The agent gets a flavor of the tool's role without a routing rule.

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