prepare_case

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

With no annotations, the description carries the full burden, and it does disclose two non-obvious behaviors: a confirmation-token gate requiring human agreement, and that measured mesh warnings force another review pass. It does not disclose side effects such as files written, idempotency of a re-run, or what a second call without a token does.

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?

Three short sentences, front-loaded with the action and followed by the two conditional guards. Nothing is padded, though the unexpanded acronyms cost the reader a little parsing effort.

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?

An output schema exists, so return values need not be described. But for a tool whose only required argument is a large multi-branch config (geometry discriminated union, mechanics, environment), the description offers no orientation to the config structure or which submode to pick — a significant gap at this complexity.

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 compensate. The phrase 'that plan's token' usefully explains confirmation_token, but the sole required parameter, config, is a deeply nested CaseConfig with dozens of fields and gets no explanation at all.

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 first sentence names a concrete verb (generate) and enumerates the pipeline artifacts (geometry/RDF/MCN/RAO) plus the mesh check, so the agent knows this is a preparation-stage tool. It is distinguishable from siblings like build_geometry or start_case, though the acronyms are never expanded and require domain fluency.

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 establishes sequencing ('before the motion solve', 'before start_case') and describes the confirmation retry path, which is real usage guidance. However, it never says when to call this instead of the closely named siblings plan_case, generate_inputs, or build_geometry, leaving the agent to infer the boundary.

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