generate_pdw

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

With annotations declaring readOnlyHint=false but destructiveHint=false, the description adds real value: 'Never overwrite' explains why a write tool is non-destructive, and 'Return the actual binary artifact and warnings' discloses the response shape, which matters because there is no output schema. 'Templates are workspace-scoped' and 'Keep private templates outside Git' add operational context beyond the annotations. It does not contradict the annotations anywhere.

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?

Six short lines, constraint-first, with no filler sentences or repeated statements. The only weakness is register: 'configure --root to their private directory' reads as CLI instructions rather than tool-call guidance, which is slightly off-target for an agent invoking a function.

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 five-parameter generative tool with nested objects and no output schema, the description covers constraints and the return artifact reasonably well but is incomplete: the acceptance-testing parameter and the io_contract are entirely unaddressed, and the relationship to generate_project_pdw is left implicit. It is enough to attempt a call but not enough to call it well.

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 carry parameter meaning, and it only partly does. It clarifies the allowed contact set inside 'rungs' (X0/X1, Y0/Y1/Y2, NO/NC, same rung count), which is genuinely useful beyond bare enum titles, but 'template_path', 'output_name', 'io_contract' and especially 'acceptance' are never mentioned, even though 'acceptance' is a complex nested acceptance-case structure whose purpose an agent cannot infer from the name 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 verb is concrete ('replace one/two X -> Y rungs in a local FBs-60MC template'), so the agent knows an artifact is being produced from a template. However, 'PDW', 'FBs-60MC' and 'X -> Y rungs' are undefined jargon, and nothing distinguishes this from the sibling generate_project_pdw, which sounds like the same operation on a different scope. Purpose is recognizable but not decidable against siblings.

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?

Usage context is implied rather than stated: 'Experimental', 'same rung count required', 'no branches, functions, comments or PLC operations' effectively define the narrow case this tool handles. There is no explicit when-to-use versus generate_project_pdw or inspect_pdw, and no statement of prerequisites beyond 'configure --root to their private directory'. The agent must infer the routing decision.

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