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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the description need not repeat safety properties. It adds a useful scoping detail about not requiring known URLs, but it does not disclose result format, pagination, or cap behavior beyond what the schema states.

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?

A single front-loaded sentence conveys the tool's purpose and primary use condition with zero filler. Every word contributes to an agent's ability to decide whether to call this tool.

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 simple two-parameter search tool with rich annotations, the description plus schema is sufficient for selection and invocation. It does not describe the exact return structure, but the schema hints at result fields (title, URL, snippet) and the annotations cover the safety profile.

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 schema fully documents both query and max_results. The description adds no parameter-level detail, so the baseline score of 3 is appropriate.

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 states a specific verb ('find') and resource ('relevant web pages'), and adds the key condition 'when you do not already know their URLs,' which clearly separates it from URL-based siblings like read_page and crawl_site. This is a precise, unambiguous definition.

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?

The condition 'when you do not already know their URLs' gives clear guidance on when to use search instead of direct navigation/reading tools. It does not explicitly name alternatives or exclusions, but the context is sufficient for an agent to route correctly among the listed siblings.

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