browser_extract

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

With no annotations at all, the description carries the full burden and does reasonably well: it discloses the auto-selection heuristic (the table/list with the most content), that file mode writes to disk and returns only a summary, and that rows are capped. It does not state read-only-ness, permissions, or failure behavior when no table/list is found.

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?

Three short sentences, front-loaded with the value proposition ('en UNA llamada') then the resource, then the scoping and file caveats. The opening phrase is slightly promotional but does convey the one-call efficiency argument. No filler sentences.

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?

Six optional parameters with no output schema mean the description must sketch the return value, and it does (rows with title, link, price, image, as JSON or CSV). Combined with the file-mode summary behavior, an agent can call this correctly; only error/empty-result behavior is missing.

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 83%, so ref, selector, file, kind and max already carry documentation. The description adds only the file-mode consequence (summary instead of full data) and the meaning of auto; format's json/csv trade-off is not explained beyond the enum itself. Baseline 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?

States a specific verb+resource: converts the most relevant table or repeated list into JSON/CSV rows. The concrete examples (productos, resultados, contactos) and the field set (título, enlace, precio, imagen) make the output shape unmistakable. It never names a sibling such as browser_read or browser_snapshot, so differentiation is left implicit.

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?

'Limítalo con ref o selector' hints at how to scope the extraction, and 'con file ... solo devuelve un resumen' clarifies the file variant. But there is no explicit when-to-use-this-instead-of guidance against the many sibling tools (browser_read, browser_snapshot, browser_eval) that also surface page content. Usage has to be inferred from the stated output format.

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