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

No annotations are provided, so the description carries the full behavioral burden. 'Deprecated' is a useful trait, but it says nothing about what the tool mutates, whether it consumes credits, what mode/format defaults imply, or what is returned.

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?

One short sentence, deprecation notice front-loaded, zero filler. Appropriate sizing for a tool that should not be called.

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 deprecated shim whose main job is redirecting to process_audio, the description covers the critical message. However, with no annotations, no output schema, and 0% parameter coverage, an agent has nothing if it is forced to fall back to this legacy path.

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% and all three parameters (mode, format, source_key) are undocumented. The description adds no meaning about any of them, leaving required 'source_key' and the mode/format enums entirely opaque.

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 never states what the tool actually does (audio stem separation); it only flags deprecation. The name and the named replacement 'process_audio' let an agent infer the domain, but the verb+resource is implied rather than stated.

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 explicitly routes the agent to an alternative ('Use process_audio instead'), which is strong when-not-to-use guidance. It stops short of saying whether there is any residual legacy case where this tool is still correct.

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