migration_trial_load_step

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

No annotations are provided, so the description carries the full safety burden. It discloses key behaviors: it writes nothing to the live books, records row-level outcomes, is idempotent on its key, and routes to a specific target workspace. This is strong for a mutation-adjacent operation, though it doesn't mention return format or error behavior.

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?

Three sentences, each earning its place: what it does, where it writes, and its idempotency behavior. Front-loaded with the action and target. No fluff or redundant restating of the schema fields.

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?

The tool has 4 required parameters, no output schema, and no annotations. The description covers the critical behavioral context—safety, target workspace, idempotency—that an agent needs to call it correctly. It doesn't specify the response shape, but that is less critical for a trial action. It could have mentioned the relationship to migration_commit_step more explicitly, but as a standalone description it is largely sufficient.

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%, so the description must compensate. It clarifies the role of workspaceId implicitly (target workspace = Testmandant), and mentions 'idempotent on its key' which explains the purpose of idempotencyKey. However, it does not explicitly explain planId, stepId, or how the idempotencyKey should be constructed. Despite that, the freeform context is better than nothing and gives meaning to the key parameters.

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 description states a specific verb, 'Trial-load a step,' with a clear target resource ('the plan's Testmandant (G12)') and explicitly distinguishes it from the live commit path ('same code path... differing only in target workspace'). This makes it easy to differentiate from siblings like migration_commit_step and migration_preview_step.

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 description implicitly communicates when to use it: when you want a trial run of a migration step against the Testmandant rather than live books. It describes behavior but does not explicitly say 'use X instead of Y' or list when not to use it. Still, the contrast with the live commit path provides clear context.

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