add_effect

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

The annotations already declare this as a non-read-only, non-destructive, closed-world mutation, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the tool autonomously chooses among installed plug-ins with a fallback to Live's native device, and 'prefer' overrides that choice. It stops short of saying where in the chain the device lands or what happens on an unrecognized role.

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 core action is front-loaded in the first clause, and the selection logic and 'prefer' override follow in priority order. The long trailing example list is justified because it teaches valid role strings that the schema does not, though the truncated ellipsis list reads slightly untidy.

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 need no explanation. However, for a 4-parameter mutation tool with zero schema descriptions, the definition leaves the target track semantics (track_index vs. track_type) and the failure mode for an unknown role or missing plug-in unaddressed, which an agent would need when the call goes wrong.

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 carries the full burden, and it covers the two most ambiguous parameters well: it enumerates representative role values ('reverb', 'eq', 'compressor', 'deesser', 'plate', 'hall', 'piano', 'strings'...) and explains that 'prefer' pins a specific device. That is the critical semantic gap filled, though track_index and track_type remain unexplained.

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 states a concrete verb and resource ('Add an effect or instrument by role') and defines the selection mechanism: prefer the best installed plug-in, fall back to Live's own device. That is specific and easy to act on. It does not differentiate itself from close siblings such as insert_device, load_plugin, or load_instrument_or_effect, so an agent must infer the boundary.

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 only implied: the role-based phrasing suggests 'use this when you want a device by function rather than by name,' and 'prefer forces a specific one' hints at when to override. There is no explicit statement of when to choose this over insert_device / load_plugin, and no prerequisites (e.g., track must exist, effect goes on an existing track vs. a return).

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