Reps

edit_routine

Destructive

Use this when the user wants to change one of their saved Reps routines: swap, add or remove exercises, or change sets, targets, order or name. First call get_routines for its routine_id, current exercises and updated_at. This writes straight away: tell the user exactly what will change (what is added, removed or adjusted) and wait for an explicit yes in this conversation. Send the FULL end state in exercises, every exercise the routine should contain, in order; anything left out is removed. An exercise the routine keeps keeps its own sets: a target or note you leave out of it stays as saved, and a target you change goes to its working sets. A timed hold or cardio takes target_duration_seconds instead of target_reps. Pass the updated_at you read as base_updated_at: if the routine changed in the Reps app since, nothing is saved and the result is routine_changed. The result lists the routine as it now stands. The change shows up in the Reps app after its next sync (up to 5 minutes) or when the app is reopened.

Input Schema

Name	Required	Description	Default
`name`	No
`exercises`	Yes
`routine_id`	Yes
`base_updated_at`	Yes
`estimated_duration_minutes`	No

Output Schema

Name	Required	Description	Default
`ok`	Yes
`name`	Yes
`exercises`	Yes
`routine_id`	Yes
`updated_at`	Yes
`exercise_count`	Yes
`visible_in_app`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 29, 2026

addedInput schema / properties / exercises / items / properties / target_duration_seconds
```
Added value: +{
+  "type": "number"
+}
```

addedOutput schema / properties / exercises / items / properties / target_duration_seconds

Added value: +{
+  "anyOf": [
+    {
+      "type": "number"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}

changedOutput schema / properties / exercises / items / required

Previous value: -[
-  "name",
-  "slug",
-  "sets",
-  "target_reps",
-  "target_weight_kg"
-]New value: +[
+  "name",
+  "slug",
+  "sets",
+  "target_reps",
+  "target_weight_kg",
+  "target_duration_seconds"
+]

First observedSep 23, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Goes well beyond the destructiveHint=true / idempotentHint=false annotations: writes immediately, requires explicit user yes, omitted exercises are deleted, kept exercises preserve saved sets/notes unless overridden, and result ordering/`routine_changed` failure mode are disclosed. Also states the up-to-5-minute app sync delay so the agent doesn't report a false failure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Long but front-loaded: purpose and prerequisite first, then write/confirm semantics, then payload rules, then failure and sync behavior. Nearly every sentence carries operational information an agent would otherwise get wrong.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-format detail is optional, yet it still names the success/failure results and the sync lag — strong for a destructive multi-param write. Slightly incomplete because several schema properties (name, rest_seconds, estimated_duration_minutes, id vs slug) have no narrative meaning anywhere.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage the description carries the load, and it does well on the risky parts: `exercises` is the FULL end state in order (omission = removal), partial target/note inheritance, `target_duration_seconds` vs `target_reps`, and `base_updated_at` as an optimistic-concurrency token. Gaps remain: `name`, `estimated_duration_minutes`, `rest_seconds`, and especially `exercise_id` vs `exercise_slug` are never explained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (change a saved Reps routine) and enumerates the exact kinds of edits (swap/add/remove exercises, sets, targets, order, name). This separates it from save_routine (creation) and get_routines (read) without the agent needing to open a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says when to use it, names the prerequisite read (call get_routines for routine_id, exercises and updated_at), and imposes a hard confirmation gate before writing. It also gives a when-not path: if base_updated_at is stale, nothing is saved.

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

All Reps tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?