Training Plan

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

Annotations only declare readOnlyHint=false, so the description carries the burden and does well: it tells the agent the plan is immutable (no post-hoc edits) and that it reports blockers rather than silently succeeding. It omits what happens on repeat calls (idempotency_key exists in schema) and any permission needs.

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?

One tight sentence, front-loaded with the core action and ending with the boundary condition. No filler.

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 description correctly conveys that planning is non-destructive. But for a tool whose single input is a complex discriminated union of four method shapes, the description never explains the method variants or how 'objective' interacts, leaving it thin relative to the schema's complexity.

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 the description says nothing about the two parameters. The large nested 'request' union (sft/dpo/rl/distill variants, training hyperparameters, idempotency_key) and the 'objective' string are entirely undocumented in prose, so the description does not compensate for the coverage gap.

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+resource ('Prepare an immutable training plan') and adds a negative scope statement ('does not launch training') that separates it from training_start/train_sft neighbors. It does not name an alternative tool explicitly, so it falls just short of a 5.

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 phrase 'does not launch training' implicitly tells the agent this is the pre-launch planning step, and 'report blockers' hints at a validation use case. However, it never says when to choose this over recipe_plan, experiment_autoplan, or training_start, so usage is only implied.

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