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

With readOnlyHint=true and openWorldHint=true already declaring the safety profile, the description adds real value by stating the return shape: all turns, with stances and sources, plus the record. It does not discuss the behavior for a nonexistent or inaccessible idea_id, nor any size/paging limits on 'every turn'.

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 sentences, no filler, and the payload description precedes the usage rule. The sentences are tersely telegraphic rather than fully grammatical, but nothing is wasted.

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?

There is no output schema, so the description must convey return content — it does so at a high level. Missing: how to get the idea_id, what happens on an invalid id, and whether a large deliberation is truncated.

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% for the single required parameter, so the description carries the burden. It implies idea_id identifies an 'idea' but gives no format, provenance, or example. Given only one param this is a mild gap, but it is not covered anywhere.

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 uses a verb ('Read') and describes the payload ('every turn with stances and sources, and the record'), which tells an agent it returns a full transcript. However, the vocabulary drifts from the tool name: it says 'idea' and 'room' but never 'deliberation', so an agent must infer that get_deliberation, 'room', and 'idea' are the same resource. That mismatch blunts the differentiation from list_deliberations and top_ideas.

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?

'Always read a room before joining it' gives an explicit prerequisite that routes the agent correctly relative to join_deliberation. It does not say how to obtain an idea_id (presumably list_deliberations or top_ideas), which is the one remaining routing gap.

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