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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description goes well beyond by stating the non-effects (no training, no spend, no version binding) and the auth requirement (approve scope or a human) for the follow-up steps. This is exactly the behavioral context a mutation tool 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?

Two sentences, front-loaded with the operation and its scope, then the constraints. Dense but every clause earns its place; 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?

For a 6-param nested-object tool with no output schema, the description covers purpose, non-effects, and scope requirements well. It does not describe the response (e.g., the created project id) but with no output schema that is a minor gap.

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 83%, so the schema already documents most parameters (name, agentId, datasetId, objective, customerId, rerunOfProjectId). The description restates the core shape ('one agent, one objective, optionally the dataset') but adds no syntax or format detail beyond the schema, so the 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 ('Open one fine-tuning pass: one agent, one objective, optionally the dataset') and immediately distinguishes the scope of the operation. An agent can tell it apart from freeze_dataset_version and decide_approval, which are named explicitly.

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?

Explicitly says when to use it and what it does NOT do ('trains nothing, binds no version and spends nothing'), then names the sibling tools (freeze_dataset_version, decide_approval) that handle those downstream decisions. Nothing is left to inference.

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