claimidx

Official

by claimidx

Overview Schema Source Related Servers Discussions Admin

Python

Local

Ask the remote ledger

claimidx_home_ask

Read-onlyIdempotent

Instructions

Rank a raw error against the remote public ledger over HTTP without importing the ledger into the local index. Auto-mints a local DID when OWNER unset and logs an ask event; returns path_b (ask alone is not a countable commons DID; path_b.next is claim --yes --share-yes after you fix it). Use when the local index is empty or stale and you want a look before claimidx_home_pull; prefer claimidx_ask for normal work because it also sees your own claims. Returns url, hit, n, pool, skipped_n, claims (each with own and src=home), path_b.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "err": "<err>"
    },
    "name": "claimidx_home_ask"
  }
}

Input Schema

Name	Required	Description
`k`	No	Maximum claims to return (default 5).
`rt`	No	Runtime as name@version, e.g. py@3.12 or node@20.18.2 (only the major is kept). Omit if unknown.
`cwd`	No	Working directory for tree-scoped evals (CLI --cwd). Pin and harness venvs stay in an isolated scratch.
`dep`	No	Packages involved as name@version, e.g. ["next@15.0.0"]. The same package at another version still ranks as a similar hit.
`eco`	No	Package ecosystem the failure occurred in: py, npm, go, rust, java, mcp, browser, ci, or other. Narrows the fingerprint; omit if unknown.
`err`	Yes	Raw error text exactly as the tool or compiler printed it (stderr line, traceback tail). Do not pre-normalize; Claimidx fingerprints it.
`url`	No	Ledger to read: HTTP(S) URL, file: URL, or local jsonl path. Defaults to CLAIMIDX_HOME (the public GitHub ledger).

Output Schema

Name	Required	Description	Default
`n`	No
`hit`	No
`url`	No
`pool`	No
`claims`	No
`path_b`	No
`skipped_n`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.7.15Oct 22, 2026

addedInput schema / properties / cwd

Added value: +{
+  "description": "Working directory for tree-scoped evals (CLI --cwd). Pin and harness venvs stay in an isolated scratch.",
+  "type": "string"
+}

Changed1 schema field changedv0.7.13Sep 26, 2026
- addedOutput schema / properties / path_b
```
Added value: +{
+  "type": "object"
+}
```

Changed1 schema field changedv0.7.7Sep 19, 2026

changedInput schema / properties / eco / description

Previous value: -"Package ecosystem the failure occurred in: py, npm, go, cargo, docker, other. Narrows the fingerprint; omit if unknown."New value: +"Package ecosystem the failure occurred in: py, npm, go, rust, java, mcp, browser, ci, or other. Narrows the fingerprint; omit if unknown."

Changed7 schema fields changedv0.7.6Sep 15, 2026

addedInput schema / properties / dep / description

Added value: +"Packages involved as name@version, e.g. [\"next@15.0.0\"]. The same package at another version still ranks as a similar hit."

addedInput schema / properties / eco / description

Added value: +"Package ecosystem the failure occurred in: py, npm, go, cargo, docker, other. Narrows the fingerprint; omit if unknown."

addedInput schema / properties / err / description

Added value: +"Raw error text exactly as the tool or compiler printed it (stderr line, traceback tail). Do not pre-normalize; Claimidx fingerprints it."

addedInput schema / properties / k / description

Added value: +"Maximum claims to return (default 5)."

addedInput schema / properties / rt / description

Added value: +"Runtime as name@version, e.g. py@3.12 or node@20.18.2 (only the major is kept). Omit if unknown."

addedInput schema / properties / url / description

Added value: +"Ledger to read: HTTP(S) URL, file: URL, or local jsonl path. Defaults to CLAIMIDX_HOME (the public GitHub ledger)."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "claims": {
+      "type": "array"
+    },
+    "hit": {
+      "type": "boolean"
+    },
+    "n": {
+      "type": "integer"
+    },
+    "pool": {
+      "type": "integer"
+    },
+    "skipped_n": {
+      "type": "integer"
+    },
+    "url": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

First observedv0.6.1Sep 3, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Discloses side effects annotations do not: auto-mints a local DID when OWNER is unset and logs an ask event, plus the important caveat that an ask alone 'is not a countable commons DID' and what path_b.next prescribes. That is real behavioral context. Minor tension: the auto-mint/log behavior is local state mutation against readOnlyHint=true, though it reads as local bookkeeping rather than a remote-ledger write.

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-loaded with the core action and the differentiator, then constraints and the alternative; every sentence carries information. It is dense and telegraphic in places (path_b, 'countable commons DID'), but nothing is padding.

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?

The tool is a 7-parameter, open-world read with an output schema, and the description covers the workflow context an agent needs: the fallback from a stale local index, the sibling to prefer, and the follow-up command. It even enumerates return fields, which is redundant given the output schema, and it omits nothing an agent would need to call it correctly.

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 every parameter including err, rt, dep, eco and url is already documented in the schema; that sets the baseline at 3. The description adds no parameter-level syntax or defaults it does not already get from the schema, only the OWNER environment variable, which is not a parameter.

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 and object: 'Rank a raw error against the remote public ledger over HTTP without importing the ledger into the local index.' It also distinguishes itself from both the local-index path (claimidx_home_pull) and the normal-work sibling (claimidx_ask), so an agent can tell the three apart 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 Guidelines5/5

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

Gives explicit when-to-use ('local index is empty or stale', 'want a look before claimidx_home_pull') and when-not ('prefer claimidx_ask for normal work because it also sees your own claims'). The alternative is named along with the reason that selects it, leaving nothing to inference.

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