plc_update_st

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

Annotations already declare mutation (readOnlyHint=false) and non-idempotency, but the description adds substantive context beyond them: the change is only staged, not committed, and the call has a side effect of promoting new globals to VAR_EXTERNAL. The explicit warning that nothing is validated or compiled is valuable behavioral disclosure, though commit/rollback mechanics are unstated.

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?

Two tight sentences: the action and its side effect come first, followed by the boundary caveats. Every clause carries information; only minor density ('newly introduced known global dependencies') costs readability.

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, and the staging-versus-committing distinction is covered. However, for a 4-required-parameter mutation tool the description omits the transaction prerequisite, the meaning of section_id, and optimistic-concurrency behavior for expected_revision, leaving real gaps.

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 coverage is only 25% – transaction_id, section_id and source have no descriptions – and the description does not explain any of them. 'ST body' hints at source, but transaction_id and section_id semantics, and how expected_revision conflicts are handled, are left entirely to inference.

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?

States a specific verb and resource ('Stage one ST body') and adds a secondary effect ('register newly introduced known global dependencies as VAR_EXTERNAL'), which separates it from the ladder-editing sibling plc_update_ld by language. It stops short of naming that sibling or any other alternative explicitly.

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?

Gives a clear exclusion: syntax/type checking and Sysmac compilation are not performed, which tells the agent to invoke validation tooling separately. It is missing positive routing (which tool to use for checking) and any prerequisite about an open transaction.

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