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

Adds substantial behavioral detail beyond annotations: describes the auto-decaying mechanism, no surcharge, tracking, and publish timing. The destructiveHint is consistent with disabling leading to hard 429, which is implied by 'Default is off (steady cap is a hard 429).'

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?

Four sentences, each adding information: action, behavior, default, and permission. No redundancy; structured logically with the core action first.

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 single-parameter toggle with no output schema and minimal annotations, the description covers what, when, behavior, default, and access requirements. It is sufficient for an agent to decide when to call and what value to pass.

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 already describes the boolean, but the description adds meaning about the behavioral consequences of true/false, such as absorbing spikes at normal credit rate and decay over time. This goes beyond the schema's basic description.

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?

Description clearly states the action ('Enable or disable the auto-decaying burst window') and the resource, distinguishing it from siblings like set_rpm_ceiling by focusing on the burst window. The verb 'Enable or disable' 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?

Provides clear context: explains when burst is useful ('brief spikes... absorbed'), default off, and requirement of edit access. Does not explicitly name alternatives, but the context makes it clear this is for toggling burst vs other settings.

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