search

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

With no annotations, the description fully carries the behavioral safety profile, and it exceeds expectations: it states count is a maximum not a guarantee, unresolved destinations are dropped rather than guessed at, sponsored rows are excluded, and results are not fetched or verified. These precise edge-behaviors are exactly what an agent needs to call it blindly.

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 definition is two sentences with no filler: it front-loads the exact resource and action, then packs edge cases and usage notes briefly. The 'pair with' instruction at the end earns its place as it improves agent execution.

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 still explains exactly what the returned results look like (title, real URL, display URL, snippet), what they exclude, and what happens in the face of unresolved destinations. It also names the natural next step (url_to_markdown). This is complete for a simple two-parameter search 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?

The schema already fully describes 'q' and 'count' with ranges and defaults, so the description does not need to add every edge. It adds meaningful contract beyond the schema by explaining that the declared number of results is a cap, not a promise, and why fewer results may be returned. That is more than a baseline, but the parameter descriptions themselves are already strong.

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 leads with 'Web search — a free-text query returns ranked organic results', which is a specific verb+resource+outcome. It details the result fields, excludes sponsored arrays, and states the hard limit of up to 25, clearly setting it apart from siblings like get_search_suggestions and url_to_markdown.

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 clear context on when this tool is used ('free-text query', returns ranked organic results) and explicitly routes follow-up consumption to url_to_markdown. It does not provide explicit 'don't use this when...' statements for similar alternatives like get_search_suggestions, so a small inference remains.

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