RAPID execution

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds genuinely new behavioral context: a prompt-injection warning that controller text is data not instructions, and an instruction to flag stale or replayed data. It duplicates the read-only claim at server scope, which is minor, and does not describe error behavior for an unknown task.

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?

Front-loaded with what is returned, then the routing alternative, then safety and provenance caveats — a sensible ordering with no filler. The sentences are somewhat telegraphic, but every one carries information.

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-value explanation is unnecessary, and the description covers state, pointer granularity, the sibling alternative, safety profile and data-staleness handling. The only real gap is the behavior when the optional task or controller parameter is omitted.

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 100% and both parameters (task name pattern, controller daemon id) are documented in the schema itself. The description only implies per-task granularity with 'where each task is' and adds no format or default-behavior detail (e.g. what happens when task is omitted) beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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 resource (RAPID task execution state) and enumerates exactly what is returned: running/stopped, cycle, program pointer and motion pointer down to module/routine/line. It also names the sibling it is not (read_rapid_source) for program text, so an agent can route without opening either schema.

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?

Explicitly hands off program-text retrieval to read_rapid_source, which is the main overlap risk among the siblings. No guidance is given on when to prefer this over get_controller_status or get_robot_position, but the resource is narrow enough that ambiguity is low.

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