Twelfth

Compare supplier offer history

compare_supplier_offer_history

Read-onlyIdempotent

Compare a supplier's latest two saved offer files: restocks, depletions, cost, availability, ETA and terms changes, new and missing lines. Use it for what-changed questions about a supplier's offers. It never proves a discontinuation from sparse snapshots; for past buying decisions use recall_decisions.

Input Schema

Name	Required	Description	Default
`limit`	No	Maximum changed rows to return (default 100).
`supplier_name`	Yes	Supplier name or key to compare.

Output Schema

Name	Required	Description
`changes`	Yes
`evidence`	Yes	How many snapshots back the comparison, and how far they can be trusted.
`truncated`	Yes
`currentAsOf`	Yes
`evidence_id`	Yes
`supplierKey`	Yes
`previousAsOf`	Yes
`currentImportId`	Yes
`previousImportId`	Yes
`source_evidence_ids`	Yes	Workspace evidence IDs backing these rows. Empty when the source carries no evidence records.
`missingLineQualification`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed12 schema fields changedOct 26, 2026
- removedOutput schema / properties / changes / items / properties / sku / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / changes / items / properties / sku / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / changes / items / properties / title / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / changes / items / properties / title / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / currentAsOf / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / currentAsOf / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / currentImportId / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / currentImportId / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / previousAsOf / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / previousAsOf / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / previousImportId / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / previousImportId / type
```
Added value: +[
+  "string",
+  "null"
+]
```
First observedOct 4, 2026

TDQS

A4.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered structurally. The description adds real behavioral context beyond that: it only looks at the last two snapshots and cannot establish discontinuation. It says nothing about pagination/limit behavior or what happens when fewer than two snapshots exist.

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, front-loaded with the core comparison scope, then usage, then the caveat and alternative. No filler, and the most decision-relevant constraint (only two snapshots) appears early.

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 shape needn't be explained, and the description covers scope, use case and a key inference limit. The one notable gap is the edge case implied by "latest two": what the tool does with a supplier that has only one or zero saved offer files.

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

Parameters3/5

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

Schema description coverage is 100%, so both parameters (supplier_name and limit with its default and max) are already documented in the schema. The description adds no syntax, format, or resolution semantics for supplier_name (name vs. key) beyond what the schema states; baseline 3 is correct.

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 (Compare) against a precisely scoped resource (a supplier's latest two saved offer files) and enumerates the dimensions compared: restocks, depletions, cost, availability, ETA, terms, new and missing lines. An agent can distinguish this from recall_decisions without opening either 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?

"Use it for what-changed questions about a supplier's offers" gives the positive trigger, and "for past buying decisions use recall_decisions" names the alternative with the condition that selects it. The caveat that it never proves a discontinuation from sparse snapshots further bounds when its output is trustworthy.

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

All Twelfth tools Inspect

Try in Browser

Pay for results, not tokens.Fund a bounty. Let AI agents compete and collaborate to solve your problems.agentbounties.appAd

Glama MCP Gateway

Add one secure layer between your agents and this server.