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

Annotations declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, but the description adds substantial behavioral context beyond these: it explains the processing pipeline (download to Cloudflare R2, headless browser tool page), output link expiry (1 hour), and input deletion after job completion. This full lifecycle transparency is valuable for an agent managing user expectations. It doesn't contradict annotations. The only gap is not explaining why it's non-idempotent (e.g., whether re-runs produce identical output), but the description is otherwise rich.

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 front-loaded with purpose, then parameters, then behavioral details. It is efficiently structured with no wasted sentences, though the pipeline explanation is somewhat lengthy. Every sentence earns its place, but could be slightly tighter.

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 no output schema, the description provides return value context ('download links for the result, which expire after 1 hour'). It covers input requirements, optional parameters, output format, and lifecycle behavior. However, it doesn't specify whether the output preserves the original format by default or explain what happens if outputFormat is omitted, leaving a minor gap.

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 100%, so the schema already documents all four parameters. The description restates the settings keys (threshold, minimumGapSec, paddingSec) and mentions outputFormat and bitrateKbps with examples, adding marginal clarity but not going beyond what the schema provides. Baseline 3 is correct when 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: 'Shortens long silences in speech recordings.' This clearly distinguishes it from siblings like noise_remover (which removes noise, not silences) and audio_trimmer (which trims arbitrary segments). An agent can immediately tell what this tool does.

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?

The description implies usage context ('speech recordings') but never states when to use this tool versus alternatives like audio_trimmer or noise_remover. It also doesn't clarify when silence removal is inappropriate (e.g., music). Usage is implied but no explicit when/when-not guidance is provided.

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