Record a user demonstration and draft a reusable playbook

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

With annotations only marking it non-read-only/destructive/non-idempotent, the description carries the behavioral load and delivers: bounded ring buffers, temporary signal listeners, a three-session cap that evicts the oldest recorder, idle self-expiry, cancel discarding data, optional metamethod hook installation, and the explicit note that the generated playbook is not auto-executed. This is far richer than the annotations alone.

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 core purpose is front-loaded, but the passage is dense and long, and the full signature enumeration duplicates the input schema, adding length without new information. Much of the remaining content earns its place, but the overall size is excessive for a description.

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 complex, 12-parameter mutation tool with no output schema, the description covers behavior, safety, failure handling ('inspect tool-schema for exact fields...'), and verification steps. An agent has enough to call it correctly and interpret results.

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 12 parameters, and the description's signature block largely duplicates it. It adds some meaning (linking includeRemoteSpy to trace-remote-traffic, the self-expiry/cap context) but no syntax or format detail beyond the schema, so the baseline 3 applies.

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+resource ('Event-driven demonstration recorder with start, poll, stop, and cancel actions') and details exactly what it observes and produces (a timeline plus a review-required playbook draft). An agent can distinguish it from siblings like playbook-save/playbook-run/session-replay without opening a schema, since it records live demonstrations rather than persisting or replaying 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?

Each action's role is spelled out (start creates, poll reads after sinceSeq, stop disconnects and returns, cancel discards) and prerequisites are named ('active-client, explicit-mutation-approval, the user is ready to demonstrate the workflow after action=start'). It also routes optional remote capture through trace-remote-traffic. However, it never states when NOT to use this tool versus alternatives like session-replay or manual scripting.

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