log_workoutRecord what the athlete actually lifted. The engine runs progression (double-progression, e1RM), detects PRs, and returns per-exercise outcomes (established/progressed/held/deloaded) with next-time targets. Weights are in kg.
| Name | Required | Description | Default |
|---|---|---|---|
| goal | No | ||
| dayIndex | No | ||
| exercises | Yes | Per-exercise completed sets (weights in kg). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full transparency burden. It discloses that the engine runs progression logic (double-progression, e1RM), detects PRs, returns per-exercise outcomes, and provides next-time targets, plus kg units. This is substantial and goes beyond a simple 'log' statement.
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 concise sentences: the first is the core purpose, the second explains the engine behavior and outputs, and the third clarifies units. Every sentence adds value and the main action is front-loaded.
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 moderately complex logging tool with no output schema, the description explains the key return data (per-exercise outcomes) and behavior (progression, PR detection). It omits semantic details about goal/dayIndex and any edge cases, but covers what an agent needs to make the call and understand the response.
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 only 33%, so the description must compensate. It adds important meaning: 'Weights are in kg' and 'completed sets' for the exercises array. However, it does not clarify goal or dayIndex semantics, leaving those under-specified. The schema provides enum/integer types but no real-world meaning.
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 opening phrase 'Record what the athlete actually lifted' gives a specific verb and resource, making it clear this is a write operation for logging completed workout sets. It distinguishes itself from read-oriented siblings like get_todays_session and get_program by focusing on recording actual performance.
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 clearly implies when to use it: after the athlete finishes lifting, to log what was actually completed. It does not explicitly name alternatives or exclusions, but the context is unambiguous enough for an agent to select this tool over read/session tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct action or resource: program retrieval, session guidance, workout logging, readiness check-in, exercise swaps, nutrition targets, and meal planning. Even the closely related list_swap_options and swap_exercise have clear separation (viewing alternatives vs. applying a change). No two tools could be reasonably confused.
Tool names are predominantly snake_case with a verb_noun pattern (get_program, list_swap_options, log_workout, regenerate_program, swap_exercise). However, a few are plain nouns (changelog, meal_plan, nutrition_targets) and readiness_checkin is a noun phrase, breaking the strict verb-first convention. This is a minor deviation that does not hinder readability.
With 10 tools, the server is well-scoped for a fitness coaching domain. Every tool addresses an essential aspect of the coaching loop: program viewing, daily session delivery, workout logging, readiness tracking, nutrition guidance, exercise modification, and explanation of changes. The count is within the ideal range and none feel redundant.
The tool surface covers the core lifecycle: get program, regenerate program, view today's session, log workout, check in readiness, swap exercises, and access nutrition targets and meal plans. Notable gaps include no explicit workout history/retrospective tool and no direct profile management, but these are likely handled externally or can be worked around. The inclusion of a changelog nicely closes the feedback loop.