Record agent activity

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, and openWorldHint=false, so safety posture is covered. The description adds genuinely new context — append-only one-event-per-call semantics, a required --allow-launchpad permission, and downstream visibility on the launchpad timeline — but leaves the failure mode (error vs. silent no-op without the flag) and event ordering/duplication behavior undisclosed.

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?

Two short sentences, zero filler, with the core action and its purpose front-loaded and the permission prerequisite following. Nothing is redundant with the title.

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 mutation tool with 20% schema coverage, no output schema, and no annotations explaining parameter roles, the description does far too little — an agent still cannot tell what runner, phase, or agent values to supply or what the call returns. Only the permission gate and the append semantics are adequately covered.

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 only 20% — just the repo parameter is documented — and the description adds no meaning for runner, phase, agent, or branch. The phase enum includes "launch" while the description only mentions "launchpad," which could mislead rather than clarify, and the required runner/phase pairing is never explained.

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?

"Append one event to the agent activity log" gives a specific verb (append) and resource (activity log), and the clause "so the launchpad's timeline shows this session" states the observable outcome. It does not explicitly contrast with write_board/read_board or other write-style siblings, so it stops 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?

Usage is implied by the stated goal (call it when you want the session to appear on the timeline), and the "--allow-launchpad" prerequisite hints at a gating condition. However, there is no explicit when-not guidance, no named alternative for recording other kinds of activity, and no explanation of what to do if the flag is absent.

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