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

The description adds context beyond annotations: timing is unverified, no ASR/charge, and warnings about inventing transcripts. Annotations cover read-only status. It doesn't describe the output format, but an output schema exists, so this is acceptable. The unverified-timing disclosure is valuable behavioral context.

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?

The description is concise and front-loaded with the core purpose and key constraints. Some sentences are dense but earn their place. Minor room for trimming, but overall efficient.

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 3 required parameters, no schema descriptions, an output schema exists, and readOnlyHint annotation, the description covers the critical behavioral warnings (no ASR, unverified timing, ambiguity handling) and input expectations. It does not explain target_phrase semantics or project_id scope, but is nearly complete.

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 indicates required fields (text, start_seconds, end_seconds) and that words come from user audio analysis, but doesn't explain target_phrase semantics (e.g., matching rules, case sensitivity) or project_id. Baseline 3 is appropriate given the description partially compensates but leaves gaps for target_phrase.

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 states a specific verb+resource: finding a phrase (target_phrase) in caller-supplied timed words. It distinguishes itself from transcription-by-ASR siblings by emphasizing 'YOUR supplied timed words; no ASR.' It does not name a specific sibling alternative, so it's clear but not fully differentiated.

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?

Explicit guidance is provided: 'Supply text/start_seconds/end_seconds for each word, from your own audio analysis. Timing is not verified by LyricPatch. Preview before generating; ask which occurrence when ambiguous. Do not invent a transcript/timestamps.' This covers when to use this vs alternatives (no ASR external call) and how to handle ambiguity.

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