Propose New Plan

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

Beyond the annotations, the description adds valuable behavioral nuance: the tool never creates directly, routes to a coach inbox for accept/reject, and automatically resolves matching newExercises entries to catalog UUIDs to avoid duplicates. This materially changes how an agent should reason about consequences and idempotency.

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?

Three sentences, front-loaded with the core purpose, followed by the two most important behavioral caveats. No filler, no repetition of schema constraints, and each sentence 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?

For a complex, nested tool with no output schema, the description covers the critical context: review-based workflow, no direct creation, and duplicate-avoidance behavior. It does not explain how to structure exercise references (catalog vs new) or what response the agent should expect, but the schema and the proposal-flow description cover most operational needs.

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 burden of explaining parameters. It explains the purpose of blocks/exercises broadly and the special behavior of newExercises[] resolution, but it does not explain the source catalog/new exercise union, temp IDs, orderIndex semantics, or target fields. The parameter names and schema structure provide some self-evidence, but meaningful gaps remain.

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 a specific verb ('propose'), a specific resource ('brand-new workout plan (blocks + exercises)'), and the delivery target ('coach inbox for accept/reject'). This clearly distinguishes it from sibling tools like propose_plan_update and propose_new_exercise by focusing on new plans routed for review.

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 clear use context: this is for proposing a new plan that will be reviewed by a human coach, not directly created. It does not explicitly name alternatives or state 'use propose_plan_update for existing plans', but 'brand-new' and the proposal flow make the primary use case unambiguous.

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