Ask teammates for decisions only people can make—budget, scope, or plan—then wait for their response. Use when context cannot decide.
Ask the team what only a person can decide (money, scope, a plan); then wait_for_teammates for the answer. Never ask what the context already answers.
| Name | Required | Description | Default |
|---|---|---|---|
| options | No | Up to four one-tap answers. | |
| question | Yes | One clear question, with what hangs on it. |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (openWorldHint=true, destructiveHint=false, readOnlyHint=false, i.e. a non-destructive write). The description adds a genuinely non-obvious behavioral trait — the call is asynchronous and the answer only arrives by then calling wait_for_teammates. It stops short of covering retraction, rate limits, or duplicate-question behavior.
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, zero filler: the first states purpose and scope, the second states the constraint and the next step. Purpose and the strongest constraint are front-loaded.
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?
Given a 2-parameter tool with full schema coverage and no output schema, the description supplies the remaining essentials: why to call it, when to refrain, and where the response surfaces (wait_for_teammates) rather than a return value.
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 100%, and both parameters ('question' and 'options', with its maxItems/length constraints) are fully documented in the schema. The description adds no syntax or format detail beyond that, so the baseline 3 applies.
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?
Specific verb ('Ask') plus target ('the team') and an explicit scope restriction ('what only a person can decide — money, scope, a plan'). It cleanly distinguishes itself from tell_people (tell vs ask) and from get_context via 'never ask what the context already answers'.
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?
States when to use it (decisions only a human can make), when not to ('never ask what the context already answers'), and the required follow-up ('then wait_for_teammates for the answer'), naming the sibling tool explicitly. Nothing about routing is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.