Enable or configure an agent

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

Annotations only say the tool is not read-only and has no open-world hint; the description adds the important guard that live agents require confirm=true and that digest agents never transmit replies/DMs. This goes beyond the structured data and materially affects how the tool should be invoked.

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 short sentences pack the core action, the configuration parameter, the confirmation guard, and an agent-behavior caveat with no filler. The most important operational information is 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?

For a moderate 4-parameter mutation tool with no output schema, the description covers what the tool does, the confirm guard, and the digest behavior exceptions. It is missing a little context around how an agent determines whether an agent is 'live' and what the returned result looks like, but these are minor given the schema and sibling list.

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?

With 0% schema description coverage, the description compensates by mapping enabled to on/off, every_ms to the interval to set, and confirm to a live-agent confirmation flag. Some agent_id values (publish_queue, health) are left to the schema enum, but the most decision-relevant parameter semantics are present.

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 the action directly ('Turn an agent on/off and set every_ms'), giving a clear verb and resource. It does not explicitly distinguish itself from sibling tools, but the behavior is specific enough to separate it from listing and scheduling tools.

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 signals a key precondition ('Live agents (if any) need confirm=true') and a meaningful exclusion ('mention_digest / inbox_digest never send replies or DMs'), which helps an agent decide when not to use those agent IDs. It does not explicitly point to alternatives, so it stops short of a 5.

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