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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, so safety framing is partly covered. The description adds real behavioral context the annotations cannot: the tool both mutates and executes, returns a compact result, and is intended to be looped. It does not state that the script is permanently modified or how a version conflict surfaces, which keeps it from a 5.

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 tight sentences: purpose first, then the alternative it replaces, then iteration guidance. Nothing is restated and no sentence is filler relative to the 11-parameter surface.

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 an 11-parameter mutation-plus-execution tool with no output schema, the description covers what it does, when to choose it, and how to continue after failure. It omits what the compact result contains and any mention of the concurrency guard, but the 100% schema coverage absorbs most of that 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 description coverage is 100%, so every parameter including patch, expected_version, and include_logs is already documented inline. The description adds no parameter-level meaning beyond 'one compact result', leaving the schema to do all the work. 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 compound verb+resource (patch a script and re-run it) plus the return characteristic ('one compact result'). Distinguishes itself from the sibling pair update_script + run_tests by naming exactly what it replaces.

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 names the alternatives ('instead of update_script followed by run_tests') and the condition that selects this tool ('collapses the fix-and-verify loop into a single round trip'). It also gives decision guidance for the iteration branch: iterate when the failure is a test defect, preserve assertions when it is an application defect.

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