ShotPulled

Preview a diagnosis

diagnose_preview

Read-onlyIdempotent

Sandbox-only diagnosis, writes nothing (no verdict, no recommendation-trail entry). Two modes: pass shot_id to dry-run a LOGGED shot (optionally overriding its sensory_tags — the "what would this read as?" preview; the shot's own bean and its age at pulled_at are used), or pass the full metric set (bean_id, grinder_id, machine_id, grind_label, dose_g, yield_g, time_s, source) for a hypothetical shot. Identical output shape to diagnose_shot, including bean_context.

Input Schema

TableJSON Schema

Name	Required	Description
`dose_g`	No	Dose in grams
`source`	No	Grinder position source — affects G1 warning (raw mode only)
`time_s`	No	Extraction time in seconds
`bean_id`	No	Coffee bean ID (must belong to this account)
`shot_id`	No	Preview a logged shot by ID (dry-run; ignores the metric params below)
`yield_g`	No	Yield in grams
`grinder_id`	No	Grinder ID (must belong to this account)
`machine_id`	No	Machine ID (must belong to this account)
`grind_label`	No	Grinder setting label, e.g. "1.1.3"
`sensory_tags`	No	Sensory observations, e.g. ["sour","bitter"]. With shot_id: replaces the stored tags for this preview (omit to use stored; [] = none).

Output Schema

TableJSON Schema

Name	Required	Description	Default
`facts`	Yes
`category`	Yes
`warnings`	Yes
`hypotheses`	Yes
`kb_version`	Yes
`bean_context`	Yes
`one_variable_only`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 12, 2026

addedOutput schema / properties / bean_context / properties / bag_id
```
Added value: +{
+  "type": "integer"
+}
```

changedOutput schema / properties / bean_context / required

Previous value: -[
-  "bean_id",
-  "bean_name",
-  "roast_level",
-  "effective_age_days",
-  "dial_category"
-]New value: +[
+  "bean_id",
+  "bag_id",
+  "bean_name",
+  "roast_level",
+  "effective_age_days",
+  "dial_category"
+]

First observedSep 6, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds concrete effect-level context: no verdict and no recommendation-trail entry are written, it is sandbox-only, and with shot_id the metric params are ignored while the shot's own bean and pulled_at age are used. That is meaningful beyond the safety hints, though permissions/rate behavior are unaddressed.

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

Conciseness4/5

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

Front-loads the key differentiator ('Sandbox-only diagnosis, writes nothing') and keeps to two dense sentences with no filler. It is information-heavy, but every clause carries load; a slight trim of the mode examples would tighten it further.

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

Completeness5/5

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

Output schema exists, so return values need no explanation, and the description still notes the output matches diagnose_shot including bean_context. With optional-everything params (0 required), the two-mode contract is fully covered for correct invocation.

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 coverage is 100%, so the baseline is 3. The description earns above baseline by explaining cross-parameter semantics the schema does not: that shot_id ignores the metric params, that sensory_tags replaces stored tags in preview mode ([] = none), and that bean age at pulled_at is used.

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 ('Sandbox-only diagnosis', dry-run preview) and immediately distinguishes it from the sibling diagnose_shot by noting it writes nothing and shares the same output shape. An agent can separate this from diagnose_shot and log_shot without opening 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 Guidelines4/5

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

Clearly enumerates the two invocation modes and the condition selecting each (pass shot_id for a logged shot vs the full metric set for a hypothetical). It implies diagnose_shot is the non-preview counterpart but never names it as the alternative for a real run, so it stops short of full when/when-not routing.

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?