Investigate on the web

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the description's job is to add operational context — and it does: depth governs how many searches and page reads are spent, cache=refresh bypasses cached answers and pages, and the reply is identical in shape to web_research. It stops short of disclosing latency, cost, or what happens when include and exclude domains conflict.

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 with zero filler; the control axes are front-loaded and the reply-parity note is the right closing clause. Nothing redundant or padded.

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?

For an 8-parameter tool with a nested domains object, the rich schema (100% coverage) and full annotations carry most of the burden, and 'Same reply as web_research' covers the absent output schema. The description is adequate, though it never touches the two required parameters (question, goal) or the cost/latency implications of depth, which matter for an open-world research call.

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%, so the baseline is 3. The description largely restates schema content (depth = searches and page reads, recency, domain filters, cache refresh) rather than adding new semantics such as how 'quick' vs 'deep' differ numerically or precedence rules for include/exclude.

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 ('Research') and enumerates the control axes (depth, recency, domain filters, cache refresh), which differentiates it from web_research via 'full control' and reply parity. It does not distinguish itself from web_lookup, web_read, or web_page, so an agent must infer that this is the multi-step agentic variant.

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?

'Same reply as web_research' combined with 'full control' implies the routing rule (use this when you need to tune cost/recency/domains, use web_research otherwise), but the alternative is never named as a choice or paired with an explicit condition. No when-not-to-use or cost tradeoff guidance is given.

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