Retrieve measured results, validation status, and local patch or report paths for a given optimization run. Use accepted=false to confirm no harness-approved changes before parent review.
Read measured results, final validation, and local patch/report paths. accepted=false means no changes are approved by the harness. Parent review is still required.
| Name | Required | Description | Default |
|---|---|---|---|
| run_id | Yes |
Changes observed during successful MCP inspections.
v0.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/closed-world, so the safety profile is covered. The description then adds genuinely useful semantics beyond them: 'accepted=false means no changes are approved by the harness' and 'Parent review is still required', which tells the agent how to interpret the payload.
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, no filler, with the core read scope front-loaded and the interpretation caveat second. Every sentence earns its place.
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?
No output schema exists, and the description partially fills that gap by enumerating the return contents (results, validation, patch/report paths) and flagging the accepted-flag semantics. It is nearly sufficient, missing only the run_id provenance and any note on error/empty cases.
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 0% and the single parameter run_id is never explained in the description – no hint about where the run_id comes from or what form it takes. With one required param and no compensating text, the agent must infer its meaning.
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 (Read) and concrete resources: measured results, final validation, and local patch/report paths. It is clearly the results-retrieval tool, though it never names how it differs from the sibling get_optimization_status.
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?
Timing is only implied – this reads the outcome of a run, so it belongs after a run completes – but there is no explicit when-to-use, no mention of the alternative get_optimization_status for in-progress checks, and no stated prerequisites for run_id.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.