mcp-ashby

Compare published pay on one board

compare_compensation

Read-onlyIdempotent

Compare pay ranges across postings on one Ashby job board, one component and one period at a time, without converting currencies or averaging. Postings that publish no range are listed by name.

Instructions

Put the pay ranges of one Ashby board side by side, one component at a time and one period at a time. Nothing is converted between currencies, summed across components or averaged: a third of the postings publish no range at all, and they are named rather than dropped.

Input Schema

Name	Required	Description	Default
`team`	No
`board`	Yes	A company name, or an Ashby board token.
`limit`	No	How many postings to compare.
`query`	No	Words to look for in the titles.
`job_ids`	No	A list of posting identifiers search_jobs returned, one to 50 of them.
`interval`	No	The period compared, 1 YEAR unless named. Postings on another period are listed apart, unconverted.	1 YEAR
`component`	No	One component at a time: a share of capital and a salary do not add up.	Salary
`department`	No

Output Schema

Name	Required	Description
`rows`	Yes
`board`	Yes
`notes`	Yes
`interval`	Yes
`component`	Yes
`not_published`	Yes	Postings whose company publishes no range, named rather than dropped.
`other_intervals`	Yes	Postings on another period, left unconverted.
`currencies_present`	Yes	Named, because rows in different currencies do not rank against each other.

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedv2.1.0Oct 30, 2026
- removedOutput schema / properties / rows / items / properties / currency / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / rows / items / properties / currency / type
```
Added value: +[
+  "string",
+  "null"
+]
```
- removedOutput schema / properties / rows / items / properties / max / anyOf
```
Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / rows / items / properties / max / type
```
Added value: +[
+  "number",
+  "null"
+]
```
- removedOutput schema / properties / rows / items / properties / min / anyOf
```
Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / rows / items / properties / min / type
```
Added value: +[
+  "number",
+  "null"
+]
```
- removedOutput schema / properties / rows / items / properties / tier_title / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / rows / items / properties / tier_title / type
```
Added value: +[
+  "string",
+  "null"
+]
```
First observedv1.0.0Aug 14, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description rightly spends its words elsewhere and does so usefully: no currency conversion, no summing across components, no averaging, and roughly a third of postings have no range but are named rather than dropped. That last point is genuinely non-obvious output behavior. Auth and rate-limit details are absent, keeping it from a 5.

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?

Two sentences, purpose front-loaded, second sentence carrying the behavioral caveats. No filler and no restatement of the title or schema.

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?

An output schema exists, so return values need not be described; the description fills the remaining gaps an agent would care about — no cross-currency or cross-component math, and missing-range postings are still listed. For an 8-parameter read tool at 75% schema coverage, this is sufficient to call correctly.

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 75%, so the baseline is 3, and the description earns an extra point by explaining the semantics behind two key parameters: component is one-at-a-time because a share of capital and a salary do not add up, and interval defaults to 1 YEAR with off-period postings listed apart and unconverted. team/department/query/limit semantics are left entirely to the schema.

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

Purpose4/5

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

Names a specific verb (compare, 'put side by side') and a specific resource (pay ranges on one Ashby board), with the scoping qualifiers 'one component at a time and one period at a time'. It is clearly distinguishable from search/lookup siblings, though it never names them explicitly.

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

Usage Guidelines3/5

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

The use case (comparing published pay across postings on a single board) is implied by the purpose statement, and the 'one component / one period at a time' constraint implicitly steers how to call it. However, there is no explicit 'use this when…' framing, no exclusion rules, and no routing to search_jobs or get_job.

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

Deploy Server