Create or replace a Bevel strength routine

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

Adds real value beyond the annotations: the write-gate requirement, the dryRun bypass, whole-object replacement semantics, and the superset limitation tied to allowDroppingSupersets. However, the annotations declare destructiveHint=false and the description openly describes replacing a routine and dropping existing supersets, a tension an agent should be warned about more directly. The opaque clause "the app also re-sends routines whole" is not explained.

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, mutation mode front-loaded, no filler or marketing language. The middle clause about the app re-sending routines whole is vague enough that it reads as a fragment rather than information, slightly weakening an otherwise tight statement.

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 six-parameter mutation with no output schema, the definition covers the essentials: write gating, dry run, replace-vs-create, exercise identity rules, and a hard limitation. What is missing are the semantics of the two allow* flags that gate risky behavior, which is the main gap for an agent invoking this cautiously.

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?

At 50% schema coverage the description must compensate, and it partially does: it explains id as the create/replace switch, dryRun's role, and the mutual exclusivity of the two exercise id types plus reps-vs-durationSec set shapes. It says nothing about allowUnverifiedValues, allowDroppingSupersets, weightUnit, or restTimers beyond the schema's own text, leaving half the surface to the schema alone.

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 ("Creates a routine") and explicitly covers the update mode ("with id, replaces an existing routine's name and exercises"), so the create-vs-replace branch is unambiguous before reading the schema. It also names the domain entities it operates on (presetWorkoutId, customExerciseId, sets), which separates it from adjacent tools like bevel_create_custom_exercise.

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 the operative condition for the replace path ("with id"), the environment prerequisite (BEVEL_ENABLE_WRITES=true), and the dryRun escape hatch, plus an explicit limitation ("Supersets are not supported yet"). It does not name a sibling alternative for related tasks such as creating a custom exercise first, so guidance is clear but not fully comparative.

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