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

Annotations already declare idempotentHint=true and destructiveHint=false, but the description adds genuinely non-structured context: the operation is asynchronous and queued as a hosted job, results are retrieved via get_job, the plan must be pre-approved by a real user, and approval fields must not be fabricated. Those are meaningful behavioral details beyond what the annotations convey.

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 short sentences, all front-loaded: the action, the async job model, and the approval guardrail. No filler, and the most important constraint (approval) is placed where the agent will read it.

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 16-parameter, 11-required mutation tool with no output schema, the description usefully covers the async job model and result retrieval path. However, it leaves the large semantic surface of the required parameters (plan, wave, revision, idempotency, workspace token) unexplained, so it is only partially 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 only 19% across 16 parameters, and the description compensates for almost none of it. It gestures at the approval requirement but never explains planId, waveId, expectedRevision, idempotencyKey, renames, labelAliases, valueRecodes, categoryOrders, or typeConversions, leaving most of the input surface undocumented.

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 gives a specific verb and resource ("Apply an approved, reversible schema repair plan") and states the reversibility/approval posture, which cleanly separates it from read-only siblings. It does not explicitly distinguish itself from adjacent mutation tools like apply_transformation or undo_change, so the sibling differentiation is partial rather than complete.

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?

It states the key precondition ("Obtain actual user approval before calling") and the follow-up step ("use get_job to retrieve its result"), which is concrete usage guidance. It stops short of naming when NOT to use it or which sibling produces the plan to apply, so it is clear context without explicit alternatives.

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