finish_turn

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

With no annotations, the description carries the full burden and does so: it discloses the mutation (ending a turn), idempotency ('safe to repeat ... never ends a second turn'), the refusal path (ok=false with end_turn carrying the blocking todo), turn-claim ownership rules with force=true takeover, autosave skipping, and progress notifications every few seconds.

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 purpose is front-loaded and the dense content is largely warranted by the tool's complex control flow, but the prose is run-on and packs several concepts per sentence, making it harder to scan than a slightly restructured version 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?

With no output schema, the description names and explains the return keys (status/turn_status, digest/turn_digest, turn, notes, turns_skipped, woke_because, ok, end_turn, turn_claim, discussion_pending, tech_popup_pending, timed_out), so an agent understands both invocation and result handling.

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 0%, yet the description gives meaning to all seven parameters: notes ('all' brings the latest eight), skip_quiet_turns=N, wake_on (event kinds or notification text, e.g. ['Machinery']), briefing=true, autosave=false, force=true, and timeout_seconds (default 600 with client-specific caveats). This fully compensates for the empty schema.

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 first sentence states a precise composite verb sequence: end my turn, wait until my turn again, and return the new turn. It clearly distinguishes itself from the sibling end_turn and wait_for_my_turn by framing itself as 'the turn boundary as one call,' so an agent can tell what it does 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 explicit when-to-use and what-to-do-next guidance for each branch: discussion_pending routes to discussion()/respond_discussion/accept_deal/refuse_deal/dismiss_discussion, tech_popup_pending routes to set_research, and timed_out says to call again. It also documents safe repetition, the skip_quiet_turns/wake_on quiet-run behavior, timeout_seconds client constraints, and points to how_to_play('finish_turn') for full detail.

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