browser_read_text

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

With no annotations at all, the description carries the full load and does disclose non-obvious behavior: visible text excludes input/textarea values, and continued reads return 'live text, which may change' rather than a stable snapshot. It omits access/auth expectations and error behavior for the editor/value modes beyond what the schema already 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?

Three short clauses, front-loaded with the core action before the caveats. Slightly dense: 'complete_source' and 'next_offset' are introduced without ever being identified as return fields, which costs a little clarity for the space they occupy.

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?

A 10-parameter tool with a nested frame object, no output schema, and no annotations needs the description to do more. It never explains the offset/max_chars pagination contract, how selector_type interacts with mode, or what the response contains, leaving the highest-complexity parts of the definition undocumented.

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 60%, so several parameters (offset, max_chars, tab_handle, frame_id, nth) rely on the schema alone. The description reinforces mode='value' and mentions complete_source/next_offset, but neither appears in the input schema, so the added parameter meaning is partial rather than compensatory.

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 and resource (read page/frame text) and scopes it to the visible-text mode by default, which tells an agent what kind of extraction this is. It does not name a sibling to disambiguate against, so an agent still has to infer why it should not use browser_snapshot or browser_evaluate instead.

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?

There is real routing guidance — 'use value for one field or snapshot profile=fields for forms' points at a mode and a different tool. However, there is no explicit when-not-to-use statement versus the other read surfaces (browser_snapshot, browser_evaluate, browser_fetch), and the pagination advice is phrased in terms an agent cannot map to a parameter.

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