throttle_recovery

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

With no annotations, the description must fully disclose behavior. It states the action is reversible (records undo) and marks risk as medium. However, it does not mention any side effects, authorization needs, or what happens if parameters are set too low/high. The reversibility is a strong point, but more could be said.

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 succinct and well-structured: a risk marker, a one-line summary, a usage context sentence, and a clear parameter list. Every sentence adds value without redundancy. It is appropriately front-loaded.

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 covers the tool's purpose, when to use it, reversibility, and parameters. It lacks examples of typical values or error conditions, but for the complexity level (a tuning tool), it is fairly complete and aids an AI agent.

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 carries the full burden. It explains each parameter: max_backfills, recovery_max_active, and target, noting that omitting leaves the setting unchanged. This adds critical meaning beyond the bare schema.

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 clearly states it tunes osd_max_backfills and osd_recovery_max_active to control recovery/backfill storms. The verb 'tune' and resource are specific, though it does not explicitly differentiate from sibling tools, most of which are read-only or have different purposes. However, the context (Ceph recovery tuning) helps an AI agent understand its role.

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 gives explicit context: use it when a recovery storm is starving client IO or when it's calm (back up). It also notes reversibility, but does not mention when not to use it or list alternative tools. The guidance is clear and actionable.

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