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

Annotations only declare the generic read/destructive/open-world flags, but the description adds substantive behavior: the preview is private, expires in 24 hours, nothing is saved to any account, every week and workout is validated, exercises are matched against the movement library, and all warnings must be surfaced before saving. That is exactly the pre-write workflow context an agent needs and cannot get from annotations.

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?

Five sentences, each doing distinct work: use case, behavior/TTL, non-persistence, required user confirmation, and exclusions. Front-loaded with the trigger condition and free of filler.

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 values need not be described. Given the nested input, preview TTL, no-account guarantee and the confirmation handoff to save_program_to_phorme are all covered, an agent has everything needed to invoke it 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?

Schema coverage is 100% with deep nested descriptions, so the schema documents the program structure fully and baseline is 3. The description only adds that the program is 'from this conversation' and that exercises get matched to the library, which is useful but modest added meaning over the 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 verb and resource ('turn a multiweek training program ... into trackable Phorme training') and explicitly scopes it away from preview_workout_import and save_program_to_phorme by excluding single workouts. An agent can distinguish it from every sibling without opening a schema.

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?

Gives an explicit when ('user wants to turn a multiweek program from this conversation into trackable training'), explicit when-not ('Do not use it for a single workout, nutrition plans or medical questions'), and the required follow-up step of asking before calling save_program_to_phorme. Nothing is left to inference.

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