Judge a solution locally

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

Beyond the annotations, the description discloses that the tool 'Executes the code you pass', warns that only trusted code should be judged, and clarifies the operation is local and costs nothing. This is valuable context the annotations do not provide.

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?

The description is three tightly packed sentences. It front-loads the core behavior and verdict list, then adds routing and safety guidance without any filler.

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?

Given the detailed schema, the presence of an output schema, and annotations, the description covers purpose, usage constraints, the key alternative, and an important safety caveat. Nothing essential for correct invocation 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?

The input schema already has 100% description coverage, so the baseline of 3 applies. The description's 'either problem_json or test_cases_json' mirrors the schema's own 'Provide this OR test_cases_json' guidance and adds little parameter-level meaning beyond it.

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?

The description states a precise verb-resource pair: 'Run a solution against test cases on this host' and enumerates the exact verdict types returned. It also differentiates itself from repovive_submit_solution by emphasizing it 'does not touch the platform' and is local.

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?

It explicitly says when to use this tool: 'Use this before repovive_submit_solution'. It also gives a concrete input constraint, 'Supply either problem_json or test_cases_json', and a safety condition, 'only judge code you trust'.

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