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

Annotations already carry destructiveHint=true and idempotentHint=true, so the safety profile is known; the description still adds value by stating 'Cannot be undone' and clarifying the exact artifact scope versus vocals. The endpoint (DELETE /files) is a useful extra detail that the annotations don't convey.

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?

Three tight sentences: action, irreversibility, alternative tool, plus endpoint. Nothing is redundant and the destructive warning is front-loaded.

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?

No output schema is needed for a delete, and the description covers scope, irreversibility, identifier provenance, and the confusable sibling operation. An agent has everything required to invoke it correctly.

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 coverage is 100% with both params documented, so the baseline is 3. The description goes beyond that by identifying the 'id' parameter as the ref_id sourced from mureka_list_files, giving the agent provenance for the value it must supply.

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 and resource ('Permanently delete a reference track you uploaded') and pins the identifier semantics with 'its ref_id from mureka_list_files'. It cleanly separates this from mureka_delete_vocal and mureka_delete_voice by naming which artifact is affected.

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?

Tells the agent the operation is irreversible and routes the singing-voice case to mureka_delete_vocal, which is genuine sibling differentiation. It stops short of spelling out prerequisites (e.g., what happens if the ref is in use by a song), so it's strong but not exhaustive.

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