ask

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

Annotations already declare readOnlyHint, openWorldHint=false and idempotentHint, so the safety profile is covered. The description adds real value beyond that: it discloses the local-model-vs-keyword fallback, the never-guesses/no-match contract, and that answers are quoted from matching records.

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?

Single dense paragraph that front-loads the core action and example before the read-only and fallback caveats. Every clause carries information; the parenthetical about local-model fallback is slightly awkward but not wasteful.

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 does the work of explaining the return payload (short quoted answer, ids, rules, handoff notes) and no-match behavior. Only the unexplained `limit` parameter and absent alternative-tool routing keep it from being complete.

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 coverage is only 33% (only `project` is documented in the schema). The description covers `project` (optional, default all projects) but says nothing about `limit`, the one undocumented parameter, and adds no format guidance for `question`.

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?

States a specific verb ('ask a question in plain words') and resource (FlowState), and describes the return shape (short quoted answer with type #id, plus rules and handoff notes). It's clearly distinguishable from data-listing siblings, but it never names the nearest alternative (e.g. `search`) to sharpen the distinction.

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 example question, states the default (all projects) and the no-match behavior, which implies natural-language lookup use. However it does not state when to prefer this over sibling tools like `search` or `get_context`, leaving the agent to infer the routing.

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