midi_list_programs

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

Without any annotations, the description carries full weight, and it delivers. It discloses the return structure (supplier and programs), the exactness of names including fixed-width padding, and the caveat that publishing names does not imply Program Change support. No contradiction with annotations (none present).

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 moderately long but each sentence contributes. The purpose is front-loaded in the first line, followed by return details, a caveat about padding, a caveat about Program Change, and the argument. It is structured but slightly more verbose than necessary; still, no sentence is wasted.

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?

Given the tool's modest complexity and lack of output schema, the description adequately covers what the agent needs: return values, parameter semantics, and behavioral caveats. It does not mention error conditions or performance, but nothing critical is missing for correct invocation. Sibling differentiation is implicitly handled.

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 input schema has no description for track_index (0% coverage), but the description explicitly says 'track_index: 0-based track index,' which adds crucial meaning beyond the integer type. It sufficiently explains the parameter's interpretation. For a single parameter, this is strong compensation.

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 opens with a specific verb-resource pair: 'List the MIDI program names a track's instrument exposes.' It unambiguously states what is fetched and from where. It also implicitly distinguishes itself from sibling tools like midi_insert_program_change (inserts) and fx_get_preset (gets full preset) by focusing on the program-name listing.

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?

The description implies usage by contrasting with REAPER's presets/*.ini (trimmed names that get rejected) and notes that passing these names straight to fx_set_preset works. It also clarifies that plugin publication of names is independent of Honor Program Change, so an agent knows when this tool is useful despite that. However, it does not explicitly name alternative tools or say 'use this instead of X' in a direct manner.

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