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

Annotations mark readOnlyHint=true, and the description aligns: 'detect', 'finds', 'computes'—no destructive actions. Adds value beyond annotations by detailing the computation (spectral overlap, conflict bands, severity, recommendation). No side effects mentioned, consistent with read-only nature.

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 expands with examples and output fields. Slightly lengthy but every sentence adds value. Could be more terse, but the structure is logical and easy to scan.

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?

Given the tool has an output schema (true), the description appropriately summarizes return fields (overlap_score, conflict_bands, severity, recommendation) without duplicating the schema. Includes usage hint (export stems first) and an integrated example. Complete for an agent to invoke 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?

The single parameter 'filenames' has 0% schema description coverage, but the description compensates excellently: explains acceptable formats (JSON array or comma-separated), provides concrete examples, and clarifies it expects stem filenames already in the exports directory. This fully resolves the parameter meaning.

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?

Clearly states the tool detects frequency masking between stems, providing concrete examples (bass/kick at 60-120Hz, guitars/vocals at 2-4kHz). Among many sibling analysis tools, this one is uniquely positioned for a specific mix problem. The verb 'detect' paired with 'frequency masking' is precise.

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 advises exporting stems first via 'export_stems', demonstrated in the example. While it doesn't explicitly state when not to use it, the context (post-export, pairwise analysis) is clear. It distinguishes from generic analysis tools by focusing on masking conflicts.

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