load_profile

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

Since no annotations are provided, the description must carry the full burden. It discloses that it validates the schema before sending and specifies the exact profile structure, which implies acceptance criteria. However, it does not mention error handling, return values, or side effects beyond setting the active recipe, leaving some behavioral gaps.

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 front-loaded with the purpose and key alternative, followed by a structured breakdown of profile and stage requirements. Every sentence contributes critical specification, with no filler or redundancy, making it appropriately sized for the complex input it documents.

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?

With no output schema and a single complex nested parameter, the description provides nearly complete input specification and notes validation behavior. It omits information about the response format or error handling, but given the depth of the parameter details, it is largely complete for the agent to invoke the tool correctly.

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 schema merely describes 'profile' as 'Full profile JSON object', but the description meticulously enumerates all required fields, types, formats (e.g., UUID v4, version: 1), and constraints like the final stage exiting on weight. This adds immense meaning beyond the schema, making it easy for the agent to construct a valid input.

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 starts with 'Load a profile JSON onto the machine as the active recipe (temporary — use save_profile to persist)', using a specific verb (load) and resource (profile JSON) while clearly distinguishing it from persistence-focused siblings. It also states the validation behavior, leaving no ambiguity about its function.

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?

It explicitly says 'temporary — use save_profile to persist', providing a clear alternative and when-not-to-use (if persistence is needed). This gives the agent a decisive guideline for tool selection among siblings like save_profile and load_profile_by_id.

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