Search Custom

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior. The description adds no extra behavioral context beyond the generic fact that it performs a search. It does not address rate limits, result variability, or how the openWorld hint impacts results, so the description contributes no value beyond the annotations.

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 a single short sentence that is easy to parse and free of redundant information. It efficiently states the core purpose, but is so terse that it lacks any usage guidance. It is appropriately sized for a simple tool though not maximally informative.

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 the tool's complexity (13 parameters, output schema present), the minimal description is sufficient for basic invocation, especially with the schema handling parameter details. However, it lacks any context about when to choose this tool over other search tools, and the return format is not summarized. The description meets a minimum viable threshold but has clear gaps in usability guidance.

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 input schema has 100% parameter description coverage, with each of the 13 parameters clearly described. The tool description itself adds no parameter-specific information. Baseline 3 is appropriate since the schema carries the full burden for parameter understanding.

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 the action ('Performs a search') and identifies the specific API ('Google Custom Search JSON API'). This distinguishes it from sibling search tools that target specific services like Gmail or Drive, though the exact scope of results (e.g., web search vs. other content) is not explicitly stated. It is more specific than a vague 'search' but lacks detailed 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?

There is no guidance on when to use this tool versus alternatives like search_gmail_messages or search_drive_files, nor any mention of prerequisites or exclusions. The description does not help an agent decide between this and other search tools.

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