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

Annotations only cover the generic write profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false); the description adds the operationally important facts: it writes immediately, it requires an explicit in-conversation confirmation, unknown exercises are refused with `candidates`, and the routine will not appear in the app for up to ~5 minutes or until the app is reopened. That is exactly the behavioral context structured fields cannot express.

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?

Front-loaded with the trigger, then the confirmation requirement, then parameter semantics — the priority ordering is right and every clause carries information. It runs long for a 3-parameter tool, and 'The result lists what was saved by name' is partly redundant given an output schema exists.

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?

Covers the write flow, confirmation gate, identifier validation, timing-vs-reps semantics, and the async sync caveat, which is more than enough for an agent to call it correctly. Two minor gaps remain: the meaning of `estimated_duration_minutes`, and no explicit handoff naming edit_routine for modifying an existing routine.

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 full load and does most of it well: it explains exercise_slug/exercise_id sourcing from get_exercise_library, the target_reps vs target_duration_seconds split with a worked example (45 for '45 s'), and that rest_seconds may be 0 for a superset. Only `notes` and `estimated_duration_minutes` go unexplained, which keeps it short of a 5.

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 ('save a new workout routine to their Reps account') and separates it from the finished-workout logging case ('a routine is a reusable template, not a log of a finished workout'). It implicitly distinguishes itself from edit_routine via the word 'new', but it never explicitly contrasts itself with the similarly-named sibling save_plan, so an agent must infer that boundary.

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-to-use trigger with a concrete user utterance ('build me a 60-minute push routine and save it'), an explicit prerequisite (describe it, then wait for an explicit yes), and an explicit retry/abandon policy when an exercise slug is refused (retry only when it is clearly what the user meant, otherwise ask). 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.