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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description still adds non-obvious behavioral context: the authoritative rule that a test passed only if this reports PASSED, and that steps.healed counts steps that only worked with a replacement selector. It omits polling cadence and behavior when the run ID is unknown.

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?

Four short sentences, front-loaded with the resource and its status vocabulary, then usage, then the pass/fail authority rule, then the healed-field caveat. No sentence restates the name or the annotations.

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?

With an output schema present, return values need not be enumerated, and the description correctly focuses on status semantics and the polling use case. For a single-parameter read tool this is close to complete, though it says nothing about error behavior for an unknown or expired run ID.

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 with 100% schema description coverage ('Run ID, as returned by Regresco tools'), so the schema already carries the semantics. The description adds nothing about runId format or origin beyond what the schema states; 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 verb and resource ('Get the real status of a run') and enumerates the exact status vocabulary (QUEUED, RUNNING, PASSED, FAILED, ERROR, CANCELLED). It also names the payload contents (timestamps, pass/fail counts), which separates it from siblings like get_run_results, get_run_failures, and get_run_artifacts.

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 a clear use case: 'Use it to follow a started run until it finishes,' which tells an agent to poll this after run_tests. It does not explicitly say when to prefer get_run_results or get_run_failures over this tool, so routing to siblings is left partly to inference.

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