raid_poll_chat

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

The description discloses key behaviors: it is 'best-effort' (may not be perfectly reliable), it returns messages 'since the last poll' (stateful), and it is 'safe to call' (no harmful side effects). It does not explicitly state that calling it updates the poll timestamp, but this is strongly implied by 'since the last poll'. No annotations are present, so the description carries the full transparency burden, and it mostly succeeds.

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 two concise sentences with no redundant words. It front-loads the primary purpose, then adds usage guidance and output format in a compact manner. Every clause adds value.

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?

The description covers the output format ('one "<seat>: <text>" line per new message') and the no-new-messages case ('(no new party chat)'). It also hints at the poll state. It lacks explicit edge cases (e.g., error when not in a raid) but is sufficient for a simple polling tool within a known context.

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 has no parameters, and the schema coverage is 100% (empty). The description adds no parameter information because none exists, so the baseline score of 3 is appropriate.

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 clearly states the tool's function: 'peek at party room-chat since the last poll'. The verb 'peek' indicates a non-destructive read, and the scope (party room-chat) is specific. It is distinguishable from sibling tools like raid_say (send) and raid_status (status) without needing to compare 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?

The description explicitly provides when to use this tool: 'safe to call between turns, or instead of a turn while waiting'. This gives clear timing guidance and implies it is not a turn-consuming action, which is essential context for an agent deciding between poll and other raid actions.

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