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

Goes well beyond the annotations: it discloses the iteration policy (apply candidates one at a time, re-evaluate, keep the first that clears without new errors), the hard scope limit (never edits outside the failing statement + inputs + param() lines), a specific refusal signal (tool.repair.out-of-region), and the fact that the caller is responsible for persisting new_code. That last point resolves what readOnlyHint=false actually means here — the tool computes, it does not save.

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 routing condition, then the mechanism, then constraints and return shape — good ordering. It is dense but every early sentence earns its place; the closing "Pass { file? | code?, ... }" list is the one redundant part given full schema coverage.

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?

Even though an output schema exists, it summarizes the return (new_code, diff, before/after health maps) and states the persistence contract, which the schema alone would not convey. For a mutating, retry-driven tool with six optional parameters, nothing an agent needs to call it safely 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 the schema already carries all six parameters including the file/code alternatives, the strategy enum values, and diagnostic id format. The description's trailing brace-list largely restates the schema; its only increment is clarifying that `diagnostic` comes from why_did_this_fail's ids, which the schema also says. Baseline 3.

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+resource (repair a CAD script) and immediately distinguishes itself from evaluate_script and why_did_this_fail by framing itself as the tool that applies a fix rather than describing one. An agent can route between the three without opening any 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?

"Use this when evaluate_script reported an error and you want the fix applied rather than described" gives both the trigger condition and the exclusion (wanting a description instead routes to why_did_this_fail). It also names the upstream dependency whose output it consumes (candidates from why_did_this_fail), so the call ordering is explicit.

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