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

Annotations only supply the generic mutation profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false). The description adds what annotations cannot: the call is NON-BLOCKING (it starts a run rather than returning a model), it is freemium-gated on a Pro plan, and it has an infrastructure dependency that can make it silently unusable. That is meaningful behavioral context beyond structured fields.

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?

Front-loaded with the action and the source requirement, and every sentence carries real information (non-blocking, plan gate, backend constraint). It is somewhat dense with parenthetical caveats, but nothing 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 five-parameter, async, gated mutation with an output schema, the description covers the source state, the pipeline behavior, the entitlement requirement, and the backend limitation. Return values are handled by the output schema, so nothing an agent needs before calling is missing.

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 all five parameters are already documented, including the paradigm default, the template_id requirement for non-mi paradigms, and the train_graph rewiring rule. The description restates the custom_data rewiring idea but adds no syntax or format detail beyond the schema, so 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 ('Train the subject's own classifier') and immediately scopes it to input from a COMPLETED calibration session, which cleanly separates it from calibration.start and execution.run. An agent can identify the tool without opening the schema.

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 explicit preconditions (session must be COMPLETED, Pro plan required, Postgres-backed backend required) and an explicit when-not (desktop-local sessions record but their upload can't be resolved by MCP train). This is exactly the when/when-not guidance that prevents failed calls.

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