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

The annotations are all false and convey little, so the description carries the full burden — and delivers extensively: exact rejection messages, refusal of steer/human posts for channel provenance, team-mode requirement, owner-scoping (foreign ids read as not found), the 500-event limit, durable channel stamping, and auth plan requirements. No contradiction with annotations: readOnlyHint=false correctly matches this append-style write operation and destructiveHint=false likewise.

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 and long, but section headers (CHANNEL PROVENANCE, REQUIRES team mode, WHEN TO CALL, WHEN NOT TO CALL, REJECTION CODES) make it scannable and the core purpose is front-loaded. It loses a point for restating the event_type and actor enums that already exist in the schema, and the prose could be tightened.

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 write tool with four required parameters, multiple refusal modes, and workflow-integration nuances, nothing an agent needs to invoke it correctly is missing: triggering conditions, ordering with me.await_steer, rejection semantics, read-back via me.sessions, and auth requirements. An output schema exists, so the absence of return-value detail is not a gap.

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?

Though schema coverage is 100%, the description adds operational meaning beyond each field: what makes a valid summary (a decision or transition, not a chat message), what ack specifically means (started working on a steer), why `human` is excluded from actor, and the ownership/team-mode constraints on session_id. The rejection-code section maps each failure to its root cause in the parameters, going well beyond the baseline for high coverage.

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 precise verb+resource pairing — 'append a TYPED TEAM EVENT to a Governed Session's timeline' — and enumerates the exact event types and actors. It distinguishes itself from siblings by naming me.await_steer as the cockpit source of steers and me.sessions as the read-back channel, so an agent can tell it apart without opening other schemas.

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?

Explicit WHEN TO CALL and WHEN NOT TO CALL sections spell out triggering situations (role handoffs, pushbacks, plan previews, hard gates, ack on steer receipt) and exclusions (not a chat log; never to record steers, which arrive via me.await_steer). It even sequences the workflow: post ack first, execute, then post handoff with the result.

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