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

Goes well beyond the readOnly/openWorld annotations: discloses rate limits (1/day per network, up to 3 failed-side tries), the audio-deletion data-retention guarantee, input size/format constraints, and the exact ceiling on duration/word count. This is the kind of operational context annotations cannot carry.

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?

Two dense sentences, front-loaded with the superset-value proposition, then limits, then input modes, then billing/data policy. Slightly list-like in the metric enumeration but every clause earns its place; no filler.

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 a 5-param, 0-required tool with an output schema already covering return values, the description supplies everything else an agent needs: scope vs. sibling, input constraints, rate policy, data retention. Nothing material is left to inference.

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%, so the schema already documents topic, context, audioUrl, mimeType and audioBase64. The description adds the either/or input rule ('Pass audioUrl or audioBase64') which is redundant with the schema, and no extra syntax or format hints. Baseline 3 applies when the schema does the heavy lifting.

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 ('Analyze a spoken recording') and distinguishes itself from sibling analyze_transcript by explicitly describing the superset relationship: 'returns everything analyze_transcript does plus delivery metrics only audio can give.' An agent can pick between the two immediately.

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?

Provides explicit hard limits (120s, 10MB, formats, minimum 30 words) and the free-tier rate policy, which effectively tell an agent when this tool is viable. However, it doesn't explicitly route a transcript-only caller to analyze_transcript or explain when to prefer one input method (audioUrl vs audioBase64) over the other.

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