stone_pou_generate

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

With no annotations, the description carries the full burden and delivers little: it doesn't say whether the skeleton is returned as text or written to a project/file, whether anything is validated or compiled, or what 'compiling' guarantees. The 'body stays yours' clause does usefully disclose that no implementation logic is generated, but that is the only behavioral fact given.

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?

A single front-loaded sentence with no filler, which is good structurally. However, its brevity comes at the cost of under-specification rather than efficiency — the one clause present is doing work that several omitted clauses should do.

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?

For a 6-parameter, zero-coverage, no-annotation, no-output-schema tool, the description leaves critical gaps: return format, whether files are created, and the meaning of most parameters. An agent could guess a call shape from the schema but cannot predict the result or side effects.

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% across 6 parameters, so the description must compensate and largely doesn't. 'typed variable sections' hints at the variables array and 'body stays yours' hints that body is a pass-through, but kind, name, comment, and return_type are never explained, and accepted values for kind are unknown (no enum).

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?

Specific verb+resource: 'Generate a compiling PROGRAM/FUNCTION_BLOCK skeleton with typed variable sections'. It names the exact artifacts (PROGRAM/FUNCTION_BLOCK) and the scope (skeleton only, body left to the caller), which no sibling tool covers. No sibling differentiation is stated, but the stone_* siblings are clearly unrelated toolchain utilities.

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?

There is no guidance on when to use this versus writing code by hand or using stone_snippet/stone_solution_create, and no prerequisites or preconditions are mentioned. The only hint of scope is the trailing clause 'the body stays yours', which implies the tool won't supply logic.

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