check_cfl

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

With no annotations provided, the description fully describes the read-only behavior: it reads MOM_input parameters, compares them, and returns an assessment. It discloses limitations but does not mention any side effects or auth requirements, which are minimal here.

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 concise with three clear paragraphs: purpose, details, and a note on limitation. It is front-loaded with the main action and contains no superfluous information.

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 tool's moderate complexity, the description covers input, process, output (stability assessment and flags), and a key limitation. An output schema exists separately, so missing return value details are acceptable.

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 parameter 'case_dir' is not described in the input schema (0% coverage). The description fully compensates by explaining it as the path to the MOM6 case directory, from which it reads DT, DT_THERM, and resolution parameters.

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 clearly states the verb 'Evaluate' and the resource 'CFL stability condition for a MOM6 case'. It distinguishes itself from sibling tools by focusing specifically on CFL stability using MOM_input parameters as a proxy.

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 provides context by noting that a full CFL check requires the actual grid file and that this tool is a quick proxy sanity check. However, it does not explicitly mention when to use alternatives like suggest_timestep or when not to use this tool.

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