Grounded web search (Gemini + Google Search)

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

With no annotations, the description carries the behavioral burden. It discloses the core behavior (grounded search with citations) and the difference between modes. However, it does not state read-only/side-effect behavior, auth needs, or rate/cost characteristics, and it leaves ambiguity about whether citations are always present given include_sources defaults to false.

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?

The description is two tight, front-loaded sentences. It establishes the core result ('grounded search with citations') first, then covers the two key controls: mode and verbosity. No filler or repetition.

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?

Given 9 parameters, no output schema, and no annotations, the description is thin. It orients the agent to mode and verbosity but says nothing about research_concurrency, max_steps, model choice, timeout, the shape of returned content, or when the citations actually appear. The schema mitigates this, but the description alone does not fully contextualize a configurable tool.

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 only light clarification that mode='normal' is a single pass and mode='research' is multi-step, which the schema already conveys. It does not add meaningful parameter guidance beyond what the schema already provides.

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?

The description clearly conveys that the tool performs a grounded web search and returns citations, and it names the two modes ('normal' vs 'research'). However, it does not explicitly distinguish itself from the sibling web_search_batch, so it falls just short of full sibling differentiation.

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?

It gives useful mode-level guidance ('normal' for a single pass, 'research' for a deeper multi-step approach) and points to verbosity for output-length control. But it never says when to prefer this tool over web_search_batch or health_check, and offers no exclusion criteria.

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