case_build

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

Discloses performance differences (container: interactive, immediate; Derecho without container: 10-30 min batch) and notes the container parameter's effect. Lacks mention of side effects or whether it modifies files.

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?

Front-loaded with the main action, then provides usage guidance. Slightly verbose for a short description, but generally clear and well-structured.

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?

Covers key usage scenarios but fails to document most parameters or describe the output. With an output schema present, lack of return explanation is partially mitigated, but parameter gaps reduce completeness.

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?

Only explains the container parameter; case_dir, sharedlib_only, and model_only are not described, despite 0% schema coverage. This leaves significant gaps for agent usage.

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 tool compiles a CESM case using './case.build'. This is distinct from siblings like case_setup and case_submit.

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?

Provides context on when to use container compilation (recommended for fast iteration) versus batch on Derecho, but doesn't explicitly mention when not to use the tool or alternatives among siblings.

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