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

Goes well beyond the readOnly/idempotent annotations by decoding the delivery-state machine (pending, scheduled, cancel_requested) and warning that 'scheduled' does not confirm Watch delivery. It also discloses negative-inference traps (recorded_workout=null is not proof of a skip; a linked recording is not proof of full interval completion) and that the server cannot see automatic scheduling state or background execution time.

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 core action and scope are front-loaded in the first clause, and nearly every sentence carries distinct operational information (state meanings, caveats, fallback). It is dense and somewhat run-on in the middle, but no sentence is 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-shape explanation is not needed, and annotations cover the safety profile. The description fills the remaining gaps an agent needs: delivery-state interpretation, the uncertainty around missing or linked recordings, and the truncation behavior — appropriate depth for a read-only listing tool.

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% and the parameter already documents 'omit for the latest 50 plans', so the baseline is 3. The description adds meaning by telling the agent where the id value comes from (a plan's uuid) and how to recover from truncation by querying a known id.

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 ('Read the latest 50 planned workouts, or one by id') plus the returned fields (prescription, delivery state, linked HealthKit workout). It also distinguishes itself from the sibling workout_detail by positioning itself as the discovery/listing step that supplies the uuid.

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 clear routing: use the returned uuid with workout_detail for analysis, ask for perceived effort, and query a known id if results are truncated. It does not state explicit when-not conditions versus siblings like data_status or session tools, but the primary follow-up path is spelled out.

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