find_by_text

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

With no annotations provided, the description carries the behavioral disclosure burden. It reveals that the tool returns every match, a total count, and per-candidate refs/ancestor paths. It could clarify the relationship between 'every match' and the schema's limit parameter, but it does communicate the core behavior.

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?

Two tightly worded sentences with no filler. The main behavior is front-loaded, the return-value detail earns its place, and the usage guidance is appended efficiently.

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?

The description compensates for the missing output schema by outlining the return shape, and the schema covers parameter details. However, the claim of returning 'EVERY match' conflicts with the limit parameter's 'Max candidates to describe,' leaving ambiguity about how many candidates are actually detailed.

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 description adds little meaning for exact, limit, or within beyond what the input schema already provides. With 75% schema description coverage, the schema does most of the parameter-documentation work; the description mainly reinforces the text parameter.

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?

States a specific operation, 'Find elements by visible text,' and names the resource. The mention of returning total matches plus refs and ancestor paths clearly distinguishes it from generic get_text or browser_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?

'Skip browser_snapshot when you know the text' is an explicit routing rule to a sibling tool. It also implies the intended use case: verifying which matched element you would actually click. It does not enumerate other alternatives, but the guidance is clear.

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