How to run Agent Chef

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

The annotations already convey that the tool is read-only and non-destructive, so the description does not need to restate that. It adds the content categories and the read-once usage pattern, but does not describe other behavior such as return size, freshness, or any caching semantics. The added value over annotations is modest.

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 compact sentences carry the entire definition with no filler. The first sentence explains what the tool is and what it contains, and the second gives concrete usage guidance, keeping key information 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 zero parameters, a full output schema, and annotations establishing safe read-only behavior, the description covers the essence of the tool and when to invoke it. Nothing needed for correct invocation is missing.

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?

The tool has zero parameters, so there is nothing for the description to add beyond what the empty schema already shows. Per the baseline rule for 0-param tools, this fully suffices.

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 identifies the tool as 'the full operating manual for agents' and enumerates its specific contents (run loop, phases, recipe-writing, messaging, safety rules), leaving little doubt about the resource returned. The action verb is only implicit in 'Read once per session' rather than an explicit retrieval verb, but the tool is easily distinguishable from all sibling tools by its documentary scope.

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?

'Read once per session' gives a clear, actionable timing instruction for when to invoke the tool. It does not mention alternatives or exclusions, but for a single-purpose manual there may be no meaningful alternative to call out, so the guidance is adequate without being exhaustive.

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