get_interactions

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

With no annotations provided, the description carries the full behavioral burden and adds several important domain caveats: dwell is not proof of attention, positions use the capture viewport rather than transformed playback frames, preparing is not absence, and labels/routes are untrusted recorded content. It does not cover auth requirements, rate limits, or explicit read-only safety, but the 'get' framing and rich semantic caveats make this strong.

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?

The description is dense but front-loaded, beginning with the core purpose and then moving through caveats and pagination. Every sentence carries weight, though the safety warning and the viewport caveat make it longer than many tool descriptions. It remains readable and free of filler.

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 read-oriented tool with no annotations and no output schema, the description covers the interaction kinds returned, pagination behavior, trust boundaries, and interpretation caveats. It does not detail the exact response fields per interaction type, but given the complexity and lack of an output schema it is largely complete for correct invocation.

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 all six parameters in detail. The description adds only marginal parameter meaning by reinforcing pagination cursor usage and 'same filters', which the schema already states. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

The description opens with a specific verb and resource – 'Get a page of prepared interaction evidence' – and then enumerates the exact interaction kinds returned (pointer samples, semantic clicks, derived drags, scroll bursts, pointer dwells, coarse typing, highlights, consented redacted routes). This clearly differentiates the tool from siblings like get_transcript or get_summary without needing to name them.

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?

It gives a concrete usage rule for pagination ('Follow pagination.nextCursor with the same filters for more') and a hint about empty results ('Preparing is not absence'), but it never states when to choose this tool over alternatives such as get_recording or get_key_moments. The intended context is implied by the content rather than explicitly compared to sibling tools.

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