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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint, so safety is covered. The description adds value beyond that: it discloses pagination behavior ('Pass last_id for the next page'), the HTTP surface (GET /files), and the shape of each returned record, which matters since there is no output schema.

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?

Front-loaded with the core purpose, then disambiguation, then pagination, then the endpoint. Sentences are dense and mostly earn their place; the trailing 'GET /files' is mild redundancy but harmless and low-cost.

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?

With no output schema, enumerating returned fields is valuable, and pagination plus account context are covered. A hint about when pagination terminates or what an empty result means would round it out, but nothing critical is missing.

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 100%, so both account and last_id are already documented. The description restates last_id's pagination role but adds no format, default, or edge-case detail (e.g., how to tell when the last page is reached) beyond the schema.

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?

States a specific verb+resource (list the reference tracks you uploaded) and enumerates the returned fields (title, duration, url, ref_id). It explicitly disambiguates from the two nearest siblings by naming them: Mureka's own library is mureka_list_references, uploaded voices are mureka_list_vocals with mine: true.

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?

Explicitly routes the agent: use this for tracks uploaded via mureka_upload_reference, use mureka_list_references for Mureka's own library, use mureka_list_vocals (mine: true) for uploaded voices. Alternatives and the condition selecting each are stated outright, leaving nothing to inference.

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