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

Annotations already declare the safety profile (not readOnly, idempotent, non-destructive), so the bar is lower, and the description still adds real context: the fixes are deterministic and free, and the change is versioned with an explicit recovery path ('undo.version_id puts the steps back'). It omits what happens on partial success or whether fixes can be listed before applying.

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 compact clauses in two sentences: what it fixes, when to reach for it, and how to reverse it. The scope limits and examples are front-loaded and no sentence is 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 single-parameter mutation tool with no output schema, the description covers purpose, cost, determinism, precedence in the workflow, and reversibility. The only real gap is return behavior — it references undo.version_id without saying what the call itself yields on success or when no fixes are found.

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?

There is a single parameter, workflow_id, and the schema already documents it at 100% coverage. The description adds no format, ID-source, or scoping detail about that parameter. Baseline 3 applies when the schema carries the full burden.

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 (fix) and scope (a workflow's steps) with a tight qualifier — 'small problems that need no AI and cost nothing' — and backs it with two concrete examples (unusable output format, misread start input). An agent can distinguish this from a general step editor 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 sequencing: use it first when a test went badly, before editing steps by hand, then re-test. That establishes both the trigger condition and the alternative it precedes. It stops short of naming sibling tools (e.g. check_test_run, edit_step) or stating when the fix set will not apply, leaving routing partly inferential.

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