discussion

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

With no annotations, the description carries the behavioral burden and mostly does: it enumerates the return payload (leader, mood, speech, buttons with id+text, deal) and flags the special screen="greeting" case that yields nothing to decide. It does not explicitly state that calling is side-effect-free, but the read-then-branch framing makes the read-only nature clear.

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 dense sentences front-load what the tool returns before covering the branch cases and the follow-up routing. Every clause carries information, though the packing of button/deal/greeting details into one sentence makes it slightly heavy.

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 zero-param, no-annotation, no-output-schema tool, the description supplies the return shape and the decision routing that structured fields cannot. It is nearly complete; only an explicit statement of read-only/no-side-effect behavior is missing.

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?

The tool takes zero parameters, so the schema provides no argument semantics to compensate for; baseline 4 applies. The description's mention of screen="greeting" clarifies a value the caller will observe rather than an argument.

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 states a specific purpose: it reads the open leader/diplomacy screen and returns the leader, mood, speech, buttons and any deal on the table. It distinguishes itself from the action siblings (respond_discussion, accept_deal, refuse_deal, dismiss_discussion) by being the read that precedes them, though the bare name 'discussion' alone would not convey this.

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 an explicit trigger ('whenever turn_status or wait_for_my_turn reports discussion_pending') and then routes to the exact alternatives for each outcome: respond_discussion(button_id), accept_deal/refuse_deal on a trade screen, dismiss_discussion for the no-button greeting case. When-to-use and which-tool-next are both spelled out.

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