Gemini web research

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

With no annotations, the description carries the full burden and does it well: runtimes (1–3 min vs 5–20 min), inline-vs-job-id return behavior, the fact that no vault is configured so deep reports are never persisted, and the 'read' vs 'unverified' source flagging. It stops short of describing quota-exhaustion or failure behavior (e.g., what happens when the Pro quota is drained), which would matter for a tool on a shared quota.

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?

Front-loaded with purpose and selection criteria, then constraints, then operational detail. Dense but every sentence — the personal-content restriction, the context-injection warning, the source-verification semantics — earns its place.

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 a tool with async job semantics, quota sensitivity, and a save path, the description covers timing, return shape, job polling, persistence, and trustworthiness of returned sources. With no output schema, the description supplies the return-value picture the agent needs.

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 description adds real value by stressing that Gemini cannot see the conversation and all context must go into `question`, which is the single biggest failure mode for this parameter. It also clarifies that `save: vault` is inert because no vault is configured, resolving a mismatch the schema alone leaves open.

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 (web research via Gemini + Google Search) and immediately scopes it: multi-source sweeps, current information, offloading Claude's context. It also implicitly distinguishes itself from the lightweight siblings by emphasizing breadth and long runtimes, and explicitly hands polling off to gemini_job.

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 explicit when-to-use (sweeps, current info, context saving), an explicit hard when-not (personal content only — never work code, client or customer data), and routes the agent onward to gemini_job for long runs. The depth quick/deep tradeoff is framed as a decision the agent can make from the description alone.

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