raw_select

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

With no annotations, the description carries the burden of disclosing side effects. It does warn that the action 'May open a dialog or change project state' and calls itself a 'Static no-argument Audacity action.' However, it does not explain what dialog might appear or what project state could change, leaving meaningful behavioral uncertainty.

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?

The description is short, but the first sentence is vague and internally inconsistent with the schema, and the second sentence packs an ambiguous side-effect warning with an unexplained instruction to inspect a command name. The information is not effectively structured or fully earned.

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?

This no-argument action has no output schema and no annotations, so the description is the only behavioral guide. It fails to say what 'Select' actually does, what audacity command it maps to, what side effects are possible, or how to obtain the command name it tells the agent to inspect.

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?

Zero parameters normally warrant a baseline of 4, but the description actively confuses the situation by saying 'based on parameters' while also describing the tool as 'no-argument.' The mention of inspecting 'the command name first' implies a parameter that does not exist, so the description misleads rather than clarifies.

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 description starts with 'Select:' which basically restates the tool name, then says 'Modify selection based on parameters' even though the schema has zero parameters. It never specifies what kind of selection is modified or how, and it does not distinguish raw_select from sibling tools like select_all, select_region, or select_clip.

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?

No guidance is provided on when to use raw_select versus the many select_* and raw_* siblings. The instruction to 'inspect the command name first' is unclear since the tool takes no arguments and no command-name parameter appears in the schema.

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