Keryx

List your completed private jobs

history_private_jobs_list

Read-onlyIdempotent

Private data for this authenticated caller only. Exact-payer completed private jobs in the current store; explicit history:read required. Bounded scan/continuation, unknown provenance and NULL own spend/creator settlement remain explicit. No wallet selector, public report/share link, model prompt, research, source fetch, signer, purchase or mutation authority.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "history_private_jobs_list"
  }
}

Input Schema

Name	Required	Description
`to`	No	Inclusive creation-time upper bound in the same UTC format; must not precede from.
`from`	No	Inclusive creation-time lower bound in UTC (Z or +00:00), retaining up to six fractional digits.
`limit`	No	Maximum completed private-job rows per bounded page, 1-25 inclusive; defaults to 25.
`cursor`	No	Private opaque cursor from this owner's previous page with identical filters; preserve it exactly.
`search`	No	Literal case-sensitive substring in your saved private-job questions, up to 200 characters.
`network`	No	Filter recorded network: eip155:5042 for Arc or eip155:5042002 for Arc testnet; selects no signer.
`surface`	No	Filter recorded job origin; missing provenance remains unknown.

Output Schema

Name	Required	Description	Default
`rows`	Yes
`scope`	Yes
`format`	Yes
`wallet`	Yes
`nextCursor`	Yes
`scanLimited`	Yes
`capabilities`	Yes
`qualification`	Yes
`scannedIntents`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedNov 7, 2026

addedInput schema / properties / cursor / description

Added value: +"Private opaque cursor from this owner's previous page with identical filters; preserve it exactly."

addedInput schema / properties / from / description

Added value: +"Inclusive creation-time lower bound in UTC (Z or +00:00), retaining up to six fractional digits."

addedInput schema / properties / limit / description

Added value: +"Maximum completed private-job rows per bounded page, 1-25 inclusive; defaults to 25."

addedInput schema / properties / network / description

Added value: +"Filter recorded network: eip155:5042 for Arc or eip155:5042002 for Arc testnet; selects no signer."

addedInput schema / properties / search / description

Added value: +"Literal case-sensitive substring in your saved private-job questions, up to 200 characters."

addedInput schema / properties / surface / description

Added value: +"Filter recorded job origin; missing provenance remains unknown."

addedInput schema / properties / to / description

Added value: +"Inclusive creation-time upper bound in the same UTC format; must not precede from."

addedOutput schema / properties / rows / items / properties / id / description

Added value: +"Exact private research ID: prv_ followed by 64 lowercase hex digits; preserve it and keep it private."

AddedOct 15, 2026

TDQS

A3.6/5.0

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, closed-world), yet the description still adds substantive context beyond them: the caller-scoped privacy boundary, the required history:read scope, bounded scanning with continuation, and the explicit statement that mutation, signer, purchase and share-link authority are absent. That is genuine disclosure an agent cannot get from the annotations. It would reach 5 with a note on what the bounded scan means in practice, e.g. total-result caps.

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

Conciseness3/5

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

The key scoping statement is front-loaded, which is correct, but the following sentences are telegraphic fragments ('unknown provenance and NULL own spend/creator settlement remain explicit') that cost the reader more than they return. The negation list at the end is efficient in intent but sprawling in execution.

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 values need not be explained, and the description still covers scope, required authorization, pagination shape and the absence of mutation authority — enough for a 7-parameter read tool. The remaining gap is the opaque phrase about NULL own spend/creator settlement, which an agent cannot confidently act on.

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 the schema already documents bounds, cursor handling, search semantics and the network/surface enums; the baseline is 3. The description adds only marginal meaning beyond that, hinting at continuation behavior ('bounded scan/continuation') and that unknown provenance is retained rather than filtered. It does not explain the exact-payer filter logic, which is the one semantic an agent might misread.

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?

The description names a specific verb-object-scope: listing completed private jobs, restricted to the exact payer and the current store, for the authenticated caller only. That is far more precise than the title alone and rules out public/shared data. It does not explicitly distinguish itself from close siblings such as history_private_jobs_detail or history_private_jobs_export, so it stops short of a 5.

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?

It supplies one real precondition ('explicit history:read required') and implies usage context via the private-only scoping, which helps an agent decide eligibility. However, it never states when to choose this over the sibling detail or export tools, nor when not to use it, so the guidance remains implied rather than explicit.

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

All Keryx 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.