plc_validate

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuine behavioral context beyond that: which diagnostics are produced, the explicit exception that "Automatic NJ/CJ offsets are not diagnosed", and the promise that coverage is reported in the result. That is real disclosure about output semantics and known blind spots.

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 long but information-dense sentences with the purpose front-loaded and the exclusions clustered at the end where they belong. Every clause carries a distinct technical fact; no filler. Slightly run-on, but structurally sound.

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 (including the explicit coverage report) need not be explained, and annotations cover safety. What is missing is the operational context: that a transaction/staged model must exist first and how this relates to the commit path. For a validation tool embedded in a transaction workflow, that prerequisite is a meaningful gap.

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?

The single parameter transaction_id has 0% schema description coverage and the description never mentions transactions, staging lifecycle, or what the ID identifies. The parameter name is somewhat inferable from sibling names like plc_begin_transaction, but the description does nothing to compensate for the coverage gap.

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?

Opens with a specific verb+resource ("Validate staged models") and then enumerates the concrete check families: ST lexer/delimiter and scalar checks, integer literal ranges, missing VAR_EXTERNAL, DataType tables, Ladder instructions. An agent knows exactly what class of analysis this performs. It stops short of naming any sibling tool, so differentiation is by scope enumeration rather than routing.

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 is implied by the coverage/non-coverage lists (partial analysis, coverage returned explicitly) and by the word "staged", which hints at a pre-commit workflow, but there is no explicit when-to-use, prerequisite, or alternative named. The negative list ("full ST grammar, Ladder semantics, DataType layout calculation, Sysmac build remain outside") does usefully tell the agent when NOT to rely on this tool.

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