ai_search

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

Annotations declare readOnlyHint=true, which the description doesn't contradict (no annotation_contradiction). The description adds meaningful behavioral context beyond the structurual annotation: markdown content inclusion, payload size implications, and render_javascript's performance trade-off. This goes beyond the minimal safety profile annotations provide.

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 three sentences covering tool purpose, a direct workflow tip (ai_scraper avoidance), and a size/performance caution. It's appropriately sized for a tool with this many parameters. Minor redundancy ('if return_content is set to True' appears twice) and a slightly repetitive structure prevent a 5, but nothing is wasted.

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 5-parameter tool with an output schema, the description covers the meaningful decision points: when to use return_content, how to set limit, and when render_javascript is warranted. The geo_location parameter is self-explanatory from the schema, and the output schema exists, so return-format explanation isn't needed. Complete without being bloated.

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 baseline is 3. The description adds significant value on top: it explains the functional consequence of return_content (avoiding an ai_scraper round-trip), warns about limit's effect on payload, and gives operational guidance on render_javascript's default-off usage. This exceeds the baseline.

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 states a specific verb+resource: 'Search the web based on a provided query.' This is unambiguous and immediately identifiable as the search-tool counterpart among siblings. However, it doesn't proactively distinguish itself from the closely-related google_search_scraper sibling, leaving the differentiation implicit.

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?

While not a formal 'when to use' statement, the description provides clear conditional guidance: it explains that when return_content=True, ai_scraper becomes unnecessary, and it recommends lowering 'limit' to reduce payload. The render_javascript guidance ('use it only if user asks to use it') is effectively a when-not-to-use instruction. Exclusions aren't exhaustive, but context is strong.

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