validate_run

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

With no annotations, the description must carry the full behavioral burden. It discloses what is checked (outputs, hashes, image paths), which is genuine behavioral content, but says nothing about side effects, idempotency, required permissions, or what a failed validation yields.

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?

Two compact sentences with no waste; the primary action is front-loaded and the usage cue follows. Appropriately sized for a single-parameter tool.

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, so the description should ideally describe what validation returns (pass/fail, which artifact failed). It omits return semantics and leaves the run_id parameter unexplained, which is insufficient for a tool whose whole value is its verdict.

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?

The single required parameter run_id has 0% schema description coverage, and the description never explains what a run_id is or where to obtain it. It fails to compensate for the schema gap on the one parameter that matters.

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 (validate) and concrete resources: final outputs, hashes, and local image paths. This distinguishes it from siblings like get_run_status and get_failure, which read state rather than verify artifacts. Clear, though it doesn't explicitly name those siblings.

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 an explicit precondition: 'Use after status reports success,' implicitly referencing the get_run_status sibling. There is no when-not guidance or mention of what to do on failure, but the trigger context is clear enough to select the tool.

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