check_checkpoint

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool 'Always returns instantly' and defines exactly what it returns: 'list of all checkpoints and any new ones.' It also explains the diff semantics for known_checkpoints. While it doesn't explicitly say there are no side effects, the 'check' framing and instant-return statement make the read-only nature reasonably clear.

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 compact and front-loaded, with the core purpose and the 'Always returns instantly' behavior stated in the first sentence. The argument list is minimal, directly mapped to the schema, and contains no fluff or redundancy.

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?

This is a simple polling tool with only two parameters and an output schema. The description covers the call pattern, the meaning of each parameter, and the default behavior when known_checkpoints is omitted. The output schema handles return-format details, so nothing necessary 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?

Schema description coverage is 0%, so the description must supply meaning beyond the schema's bare types and titles. It does this thoroughly: run_id is defined as 'The run to check,' and known_checkpoints gets a full explanation including how new files are computed and the default behavior when omitted. This is richer than the schema alone.

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 specific verb and resource: 'Check if new .onnx checkpoint files appeared on disk.' It also adds the key behavioral detail that it 'Always returns instantly,' which clearly separates it from blocking wait tools. The mention of .onnx checkpoint files differentiates it from check_step, check_reward, and check_completion.

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 gives clear context for when to use the tool: checking for newly appeared checkpoint files during a run. It explains the polling pattern by telling the agent that known_checkpoints should come from a previous call and that new files are the current set minus the known set. It does not explicitly mention when not to use it or name alternative tools, but the intended use case is unambiguous.

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