add_question

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

With zero annotation coverage the description carries the full burden and does well: it discloses auto-labelling (do not supply your own id), the multi-decision warning, and the side effect that a blocking question moves a designed initiative back to draft. It does not state permissions, error behavior, or what the response payload looks like beyond `id`.

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?

Front-loaded with the core action, then constraint, then side effect, then the optional flag — a sensible order. The parenthetical warning is dense but informative; nothing is padding, though the sentence is long-winded enough to slow an agent scanning it.

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 4-parameter mutation with no annotations and no output schema, it covers side effects and the id return convention well, but leaves the `collection` parameter and the return shape ambiguous. Adequate but with visible gaps.

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 25% (only `ref` is documented), so the description must compensate. It adds real meaning for `implementation` and clarifies that labels are generated rather than passed, but says nothing about `text` or `collection`, leaving half the parameters undefined 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?

Clear verb+resource: 'Add an open question' with the domain constraint 'one decision per question'. It distinguishes itself from a split/pose-many flow by telling the agent to pose several as separate questions, though it never names the sibling tools it relates to (split_question, next_question).

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 concrete decision rules: one decision per question, use implementation=true for questions left to the implementer, and be aware a blocking question reverts an initiative to draft. No explicit exclusions or named alternatives, so it stays at 4 rather than 5.

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