expand_recommendation

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

With readOnlyHint=false and destructiveHint=false, the annotations only say 'a non-destructive write.' The description adds genuinely new behavior: accepting yields a 'trial brief, not execution,' which clarifies the side effect is preparatory rather than committing. It still doesn't state permissions, idempotency, or what the four actions do.

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 precondition and with no filler or repetition. The brevity comes at the cost of under-explaining 'four native actions' and 'trial brief,' but no sentence 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?

An output schema exists, so return values needn't be described, and the gating condition plus the trial-brief caveat cover the two riskiest aspects of invocation. However, for a three-required-parameter mutation with zero schema documentation, the description leaves too much (especially expected_revision) unexplained.

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 0% and all three parameters are required, yet the description says nothing about recommendation_id, task_id, or the concurrency-sensitive expected_revision. The description therefore does no work to compensate for the undocumented schema, leaving expected_revision especially opaque to a calling agent.

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 verb+resource is present (expand a recommendation into 'four native actions'), but 'native actions' is unexplained jargon and the description never states what a recommendation is or how this differs from get_recommendation or propose_recommendation. An agent gets the general shape of the operation but not a precise definition of what is produced.

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?

The opening clause 'Only after user asks to expand' is an explicit, actionable precondition that tells the agent when NOT to call it, which is stronger than most definitions. It stops short of naming alternatives or describing what to do instead when the precondition is unmet.

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