live_plugins

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

With no annotations present, the description carries the full behavioral burden; it discloses that this is a read-style enumeration of installed plug-ins and which plug-in formats are covered. However, it says nothing about what each entry contains beyond a name, ordering, or what happens when nothing matches. Given zero annotation coverage, more disclosure of the return shape and failure modes would be expected.

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?

It is a single front-loaded sentence with no filler, but the heavy nested parentheticals ('default; the names live_add_plugin and live_add_send take') make it harder to parse than necessary. The information is dense and useful, just awkwardly structured.

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?

There is no output schema and no annotations, so the description is the only source of behavioral detail, and it leaves the `filter` parameter entirely unexplained and does not describe the shape of returned entries. For a lookup tool whose whole value is producing names an agent will feed into add_plugin/add_send, this is under-specified.

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 description coverage is 0%, so the description must explain both parameters. It handles `kind` partially — it names the instrument case and its enum value and the effects default — but never states the literal value "effect" even though the enum contains it. The `filter` parameter is not mentioned at all, leaving half the parameters undocumented in both schema and prose.

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 names a specific resource (plug-ins installed in the running Studio One, covering PreSonus, VST and AU formats) and its scope (by name, optionally filtered by kind). It also ties itself to the sibling tools that consume the returned names (live_add_plugin, live_add_send, live_add_instrument_track), which distinguishes it from live_plugin_params or live_inserts. The only weakness is that the verb is implicit in a noun phrase rather than stated as 'list'.

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?

It states the default behavior (audio effects) and how to switch to instruments, and it identifies the downstream tools that consume the output, which tells an agent when this list is the right input source. It does not explicitly say when not to use it or how it relates to live_inserts/live_plugin_params, so a small amount of inference remains.

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