choose_goalStart the goal the person picked. It goes to the Agents Bar on its own, like start_quest.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | suggestion_id from suggested_goals data.suggestions[] | |
| request_key | Yes | Idempotency key: reuse it on retry, new per action |
Changes observed during successful MCP inspections.
Input schema / properties / request_key / descriptionPrevious value: -"Your idempotency key, 16-128 of [A-Za-z0-9_:-]; reuse it on retry, new per action"New value: +"Idempotency key: reuse it on retry, new per action"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the mutation/idempotency/open-world profile, so the bar is lower. The description does add real context beyond them: the chosen goal is placed in the Agents Bar automatically, so the agent needn't take a follow-up action. It omits failure behavior (invalid or already-consumed suggestion_id) and any permission requirements.
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 with no filler, and the primary action is front-loaded. It is terse almost to a fault, but nothing in it is wasted.
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 two-parameter, fully documented tool with rich annotations and no output schema, the description covers the essential effect. It leaves gaps around idempotency behavior (partially implied by 'like start_quest'), error cases for a stale suggestion_id, and confirmation of what the caller sees after the goal starts.
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%, with both parameters documented (suggestion_id source, idempotency key semantics), so the baseline is 3. The description itself contributes nothing about parameters, which is acceptable given the schema does the work.
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 ('Start the goal'), and the qualifier 'the person picked' scopes it to a suggestion selected from suggested_goals. The comparison 'like start_quest' helps an agent separate it from that sibling, though the relationship to suggested_goals is only made explicit in the schema, not the description.
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 is implied ('the person picked') rather than stated as a rule: no explicit 'call this after suggested_goals' or 'do not use this to create a brand-new goal'. The reference to start_quest hints at the alternative but never says when to prefer one over the other.
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.