session_act

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

Annotations only cover readOnly/destructive/idempotent/openWorld flags. The description goes well beyond them: it enumerates what `observed` returns, states that request bodies and query strings are never captured, that dialogs are auto-dismissed and popups recorded then closed, and that leaving allowlisted hosts closes the session and halts extraction.

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 action, then the return contract, then the locator-derivation and side-effect warnings. Dense but every sentence carries operational information; the single long paragraph is slightly harder to scan than a bulleted form would be.

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 five-parameter, nested-schema mutation tool with no output schema, the description supplies the return shape (URL/title plus `observed` categories), the locator provenance rule, the allowlist failure mode, and the extraction-folding option. Nothing essential for correct invocation 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 coverage is 100%, so baseline is 3; the description still adds usable semantics by explaining that action locators should be sourced from a prior extraction's `playwright` expression and that `then_extract` defaults to a diff in the same call. It adds routing/derivation guidance rather than restating field docs.

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 (perform a declared action list of fill/click/press/select/goto/wait) on a specific resource (an open session's main frame) with scope limits (max 20). An agent can distinguish this from extraction/verification siblings without opening the schema.

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 clear operating context: derive locators from a prior extraction and paste its `playwright` expression, pass `then_extract` to fold the snapshot into the same call, and the allowlist consequence. It does not explicitly name alternative siblings (e.g. when to prefer session_extract or extract_semantic_dom_after), so it falls just short of a 5.

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