do_train

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

With no annotations supplied, the description carries the full burden and does well: it discloses two execution paths (local JEV probe vs. tiered trainer), that confirm triggers a paid-gated job after a smoke run, and that repeated calls are polling rather than re-training. It omits permission requirements, failure behavior, and what force or training_free_confirmed override.

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?

Dense and front-loaded: the purpose leads, the payload signature follows, then path behaviors. Bracket notation for optional fields is efficient. Some jargon ('JEV probe', 'Tiered path with a trainer') costs a little clarity 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 need not be spelled out. For a cost-incurring mutation with a nested, undocumented payload, the description covers the critical decision points (estimate vs. launch vs. poll) and two execution modes. Only the meaning of the override flags is left uncovered.

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% and the sole parameter is an open 'payload' object, so the description must compensate. It does list the payload keys (point_id required, dry_run, confirm, training_free_confirmed, force), which is essential, but it never explains the semantics of training_free_confirmed or force, leaving two flags opaque.

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: 'Train the decision model for a point.' An agent can tell what the tool produces. It does not, however, differentiate itself from the sibling dm_train, which on name alone looks like the same operation, leaving ambiguity about which to pick.

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?

Gives a clear invocation sequence: dry_run to see the estimate and joining points, confirm to launch (smoke first, then the paid-gated full job), and repeat calls to poll status. That is real when-and-how guidance, though it offers no exclusions or comparison against the dm_* siblings.

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