add_reference

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

With no annotations, the description carries the full burden of behavioral disclosure. It states the primary mutation (adding a local file to the library) and the optional favorite side effect, but it does not say whether the file is copied or moved, whether duplicates are allowed, whether the operation is reversible, or what happens on invalid paths or unsupported audio formats.

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?

A single sentence front-loads the main action and uses a parenthetical for the optional favorite behavior. There is no filler, and every phrase conveys useful 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?

For a simple three-parameter add operation, the description provides enough to attempt a basic call: a path and a favorite flag. But complete invocation still depends on knowing name semantics, file handling behavior, and possible failure modes, none of which are covered.

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 compensate. It adds meaning for 'path' by calling it a local audio file and for 'favorite' by explaining the set_target(kind='favorites') implication, but it never clarifies the optional 'name' parameter, leaving a real semantic gap.

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 and resource: 'Ingest a local audio file into the reference library.' It also differentiates itself from siblings by clarifying that this tool adds content, while find_references and set_target operate on or consume the reference library.

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 intended use is implied by 'ingest a local audio file into the reference library,' and the parenthetical ties favorite tagging to set_target. However, it does not explicitly state when to prefer this tool over find_references, project_reference, or place_sample, nor does it mention exclusions or prerequisites.

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