ShotPulled

Update a shot

update_shot

DestructiveIdempotent

Correct fields on an already-logged shot in place, with no need to delete and re-log. Use for fixing a wrong dose/yield/time or grind label, re-filing a shot onto the right bean (bean_id), backfilling rating/tasting notes, or fixing the timestamp (pulled_at). Changing grind_label re-derives the numeric grind position from the shot's grinder; changing yield/time/dose/tds keeps flow rate and extraction yield consistent automatically.

Input Schema

Name	Required	Description	Default
`fields`	Yes	Only the fields to change
`shot_id`	Yes	ID of the shot to correct

Output Schema

Name	Required	Description	Default
`status`	Yes
`message`	Yes
`shot_id`	Yes
`updated_fields`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 3, 2026

addedInput schema / properties / fields / properties / machine_settings

Added value: +{
+  "description": "The machine's selector positions for this shot, {key: position}; replaces what was stamped, null clears it",
+  "maxProperties": 16,
+  "type": [
+    "object",
+    "null"
+  ]
+}

Changed2 schema fields changedSep 12, 2026

addedInput schema / properties / fields / properties / bag_id

Added value: +{
+  "description": "Re-file the shot onto this bag; must be a bag of the shot's bean",
+  "type": "integer"
+}

changedInput schema / properties / fields / properties / bean_id / description

Previous value: -"Re-file the shot onto this bean"New value: +"Re-file the shot onto this bean (its current bag, unless bag_id is also given)"

Changed1 schema field changedAug 17, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "message": {
+      "type": "string"
+    },
+    "shot_id": {
+      "type": "integer"
+    },
+    "status": {
+      "type": "string"
+    },
+    "updated_fields": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "status",
+    "shot_id",
+    "updated_fields",
+    "message"
+  ],
+  "type": "object"
+}

Changed9 schema fields changedJul 19, 2026

addedInput schema / properties / fields / properties / data_confidence / description

Added value: +"estimated marks the metrics as a best guess instead of burying the caveat in notes"

changedInput schema / properties / fields / properties / data_confidence / enum

Previous value: -[
-  "measured",
-  "recalled"
-]New value: +[
+  "measured",
+  "recalled",
+  "estimated"
+]

addedInput schema / properties / fields / properties / flavor_notes / description
```
Added value: +"null clears the notes"
```
changedInput schema / properties / fields / properties / flavor_notes / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```
addedInput schema / properties / fields / properties / rating / description
```
Added value: +"1-5; null clears the rating"
```

changedInput schema / properties / fields / properties / rating / type

Previous value: -"integer"New value: +[
+  "integer",
+  "null"
+]

addedInput schema / properties / fields / properties / tasted

Added value: +{
+  "description": "Backfill 1 to mark a pending shot as tasted-clean (tasted, no defect tags) so it leaves the taste-pending queue without inventing a tag or rating",
+  "enum": [
+    0,
+    1
+  ],
+  "type": "integer"
+}

addedInput schema / properties / fields / properties / verdict / description
```
Added value: +"null clears the verdict"
```
changedInput schema / properties / fields / properties / verdict / type
```
Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
```

AddedJul 14, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is known. The description adds valuable behavioral context beyond that: it clarifies this is an in-place correction (not a deletion), and it discloses automatic re-derivation of numeric grind position and consistency maintenance for flow rate and extraction yield when changing key fields. Permissions and error behaviors are not addressed, but the core behavioral traits are surfaced.

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?

Three sentences with zero waste: first states purpose and scope, second lists common use cases, third covers derived-field behavior. The purpose is front-loaded and every sentence earns its place.

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?

With an output schema and annotations present, the description needn't explain return values or safety flags. It covers purpose, use cases, and key behavioral side effects. Minor gaps remain, such as validation constraints (e.g., bag_id must belong to the shot's bean), but those are documented in the schema.

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?

Schema description coverage is 100%, so baseline is 3. The description adds meaning beyond the schema by explaining that changing grind_label re-derives the numeric position and that changing yield/time/dose/tds keeps flow rate and extraction yield consistent. It also calls out bean_id for re-filing, though that is already described in the schema.

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 ('Correct') and resource ('already-logged shot') and immediately distinguishes itself from delete+re-log. An agent can tell it apart from delete_shot and log_shot without opening any 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?

Enumerates concrete scenarios for use: fixing dose/yield/time/grind, re-filing onto the right bean, backfilling rating/tasting notes, correcting timestamp. It also implies the alternative (delete and re-log) and asserts it is unnecessary, giving clear routing guidance.

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

All ShotPulled 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?