Find in page snapshot

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

Annotations already declare readOnlyHint: true and destructiveHint: false, so the tool's safety profile is clear. The description adds valuable behavioral detail: it returns 'matching snapshot nodes with a few lines of surrounding context (like search snippets)', which is not obvious from annotations alone. This goes beyond the annotation data and helps the agent understand the return format.

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, well-structured sentence. It is front-loaded with the core purpose ('Search the accessibility snapshot') and efficiently adds return format and cost context in the same sentence. No wasted words.

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 that this tool has no required parameters, no output schema, and relatively low complexity, the description is fairly complete. It explains what it does, what it returns, and the trade-off vs. browser_snapshot. A slight gap is the lack of mention that text and regex might be mutually exclusive, and no example of the return format. But overall, for a non-complex tool, it covers the essentials well.

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 0%, so the description must compensate. It does mention that the tool searches for 'text or a regular expression', which semantically covers the 'text' and 'regex' parameters. However, it does not explain the '_meta' parameter at all, nor does it specify how to choose between text and regex (e.g., mutual exclusivity). With 3 parameters and some coverage, a 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 explicitly states the verb ('Search'), the resource ('accessibility snapshot of the current page'), and the query types ('text or a regular expression'). It clearly distinguishes this tool from siblings by focusing on search within the snapshot for element location, as opposed to browser_snapshot which captures the whole snapshot.

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 description provides clear context for use: when you need to locate an element and its ref, and contrasts it with capturing the whole snapshot, offering a cost-benefit argument ('cheaper'). However, it does not explicitly state when NOT to use it (e.g., when you need the entire snapshot structure) or list alternative sibling tools by name, though the contrast with 'whole snapshot' implicitly references browser_snapshot.

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