llm_answerAnswers one job from llm_poll. answer must be an object matching that job's inputSchema. A wrong shape is refused with the reason and the job stays open, so correct it and call again.
| Name | Required | Description | Default |
|---|---|---|---|
| jobId | Yes | The jobId from llm_poll. | |
| answer | No | The answer, matching the job's inputSchema. |
| Name | Required | Description | Default |
|---|---|---|---|
| ok | No | True when it was accepted. | |
| reason | No | Why it was refused, when it was. |
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": true,
+ "properties": {
+ "ok": {
+ "description": "True when it was accepted.",
+ "type": "boolean"
+ },
+ "reason": {
+ "description": "Why it was refused, when it was."
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare the write/non-idempotent/non-destructive profile. The description adds real behavioral context beyond them: validation is enforced against the job's inputSchema, failures are refused with a reason, and the job remains open on failure rather than being consumed. It does not say what happens to the job after a successful answer, which is the main remaining gap.
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 short sentences, front-loaded with the core action, followed by the validation and retry rule. Nothing is redundant or padded.
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?
An output schema exists, so return values need no explanation, and the origin of jobId is stated. What is missing is the post-success lifecycle (whether the job is closed or must be re-polled), which an agent calling this tool would reasonably want to know.
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%, so both jobId and answer are already documented, including that answer must match the job's inputSchema. The description restates the same constraint and adds the failure consequence, but contributes no new meaning about the parameters themselves; 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?
States a specific verb and resource: 'Answers one job from llm_poll.' The reference to llm_poll implicitly separates it from the poll-side sibling, though it does not name llm_detach or other llm_* siblings to clarify the boundary further.
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?
Usage context is clear: it is the response half of the llm_poll loop, and the retry path is spelled out ('correct it and call again'). It does not explicitly state when not to use it or how it relates to llm_detach, but the when-to-use condition is unambiguous.
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.