How to run Agent Chef

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds that it is a manual to be read once per session, but does not disclose size, return format, or any behavior beyond annotations. With annotations doing substantial work, a 3 is appropriate.

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?

A single dense sentence that front-loads the resource and enumerates contents compactly, ending with the actionable cadence. Every phrase earns its place.

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?

An output schema exists, so return-value details are unnecessary here. For a zero-parameter documentation tool with annotations and an output schema, the description covers what it is, what it contains, and when to call – essentially complete. Minor gap: no hint about size or format.

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 parameters, the baseline is 4. The description confirms no configuration is needed by treating it as a pure read with no inputs. Nothing further is required for an empty 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?

States a specific resource (the full operating manual for agents) and enumerates its contents: run loop, phases, recipe writing, messaging, safety rules. It is clearly distinguishable from any sibling, all of which are operational tools rather than documentation. A 5 would require naming the verb as precisely as 'retrieve'; here 'the full operating manual' functions adequately but is slightly noun-heavy.

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' is explicit, actionable guidance on when to invoke. It provides clear context for frequent agents. No alternatives or exclusions are named, but no sibling overlaps with this tool's role, so the omission is minor.

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