nex_browser_get_text

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

Consistent with readOnlyHint=true, so no contradiction. It adds useful behavioral context (only visible text is returned; CAPTCHAs block this endpooint and must be handled through the dedicated prepare tool, not via CDP/Python/image matching). It does not say what the response looks like, whether hidden or off-screen text is excluded, or whether output is truncated on large pages.

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?

Front-loaded with the core action, then the CAPTCHA caveat. Every sentence is short and carries a directive, though roughly half the text is CAPTCHA policy rather than text-extraction semantics, which is a slight imbalance for a read 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 3-optional-param, read-only extraction tool with full schema coverage and no output schema, the description is adequate but incomplete: it omits the return shape (single text blob?), behavior on pages with no visible text or iframes, and only points at the first step of the CAPTCHA flow (prepare) without the submit/complete follow-through it references elsewhere in the family.

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 100%, so the schema already documents pageId, target, and sessionId defaults. The description reinforces the 'one target' concept (snapshot ref e12 or unique CSS selector), but adds no format or edge-case detail beyond the schema; baseline 3 is met and the 'one target' scoping nudges it slightly higher.

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: 'Read visible text from the page or one target.' That is more precise than a generic 'get text' because it scopes the read to rendered/visible content and to an optional single target. It does not explicitly contrast with the nearest ambiguous sibling (nex_browser_snapshot), so it falls short of a 5.

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?

Gives explicit routing only for the CAPTCHA case: use nex_browser_captcha_prepare first, and do not hand-roll CAPTCHA solving. The main selection question an agent faces — this tool vs nex_browser_snapshot vs nex_browser_evaluate for extracting content — is left unaddressed.

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