Answer a thread's clarifying questions (status must be awaiting_answers).
`answers` is a list of {"idx": <int from get_request_status>, "answer_md":
<str, 1..2000 chars>}. Answer EVERY question exactly once. Flips the thread
back to intake_pending; poll get_request_status again.
| Name | Required | Description | Default |
|---|---|---|---|
| answers | Yes | ||
| thread_id | Yes | ||
| project_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses a concrete side effect: 'Flips the thread back to intake_pending'. It also instructs to poll get_request_status again, which reveals the post-condition and expected follow-up. This goes beyond the annotations, which only indicate that the operation is not read-only and may be destructive.
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 compact and front-loaded with the core action and precondition. Every sentence adds value: the answers format, the exactly-once requirement, and the state transition. No filler or repetition.
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 the tool's complexity, the description covers the key requirements: how to format answers, the mandatory status condition, the effect on thread state, and the next step. An output schema exists, so return-value documentation is not the description's burden. Could add error-handling behavior for invalid idx values, but not essential.
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 0%, but the description compensates by detailing the `answers` parameter structure with `idx` and `answer_md`, including types, source, and length constraints. It also enforces 'Answer EVERY question exactly once'. Project_id and thread_id are not described, but their purpose is evident from their names.
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 specific verb and resource: 'Answer a thread's clarifying questions' and immediately specifies the required state ('status must be awaiting_answers'). This makes the tool's purpose clear, though it does not explicitly contrast it with sibling tools like refine_request or get_request_status.
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 clearly states when to use the tool: the thread must be in awaiting_answers status. It also gives operational guidance, like answering every question exactly once and polling get_request_status afterward. However, it doesn't name alternatives or explicitly state when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.