local_gpu_record_review

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

With no annotations, the description carries full burden for behavioral disclosure. It only says 'record' without detailing side effects, persistence behavior, requirements (e.g., round must exist), or how the evidence is stored.

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 a single, front-loaded sentence with no fluff. However, given the tool's 10 parameters and nested structure, one sentence may be too terse to be truly helpful, but it earns high marks for conciseness.

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?

Despite having an output schema, the description is inadequate for a tool with this complexity. It fails to explain key concepts like stage_checks vs visual_checks, the meaning of next_action, or the relationship to generated rounds.

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 description adds no parameter-level meaning. It does not mention any of the 10 parameters (run_id, round_number, scores, etc.) or explain their roles.

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 uses a specific verb ('record') and resource ('review evidence for one generated round'), clearly distinguishing this tool from siblings like local_gpu_generate_round or local_gpu_finalize_run.

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?

The description implies a usage context (recording evidence after a generation round) but does not explicitly state when to use this vs alternatives like get_run or generate_round. No exclusions or when-not guidance provided.

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