Skip to main content
Glama
Sign In
Align CLI

Align CLI

Official
by aligndottech
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

align_backfill

Imports older history from an already connected source into the local graph when users need context beyond stored data. Runs in the background, reads only, and starts only if the source is connected.

Instructions

Import more history from a source the user has ALREADY connected (for example the last year of GitHub PRs) into the local graph on this machine. Offer it when the user asks for older context than the graph holds. It runs in the background, only reads from the source, and makes no LLM calls. It never takes a token or key: if the source is not connected, or its saved token was refused, nothing starts and the reply gives the exact align connect <source> command for the user to run themselves. Do not ask the user to paste a token into the chat.

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": {
      "source": "<source>"
    },
    "name": "align_backfill"
  }
}

Input Schema

NameRequiredDescriptionDefault
sinceNoHow far back: 30d, 2w, 6m, 1y or all. Default 180 days. A ceiling per source still applies
sourceYesWhich connected source to read from

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only supply readOnlyHint=false and destructiveHint=false, and the description goes well beyond them: background execution, read-only against the source, no LLM calls, no token handling, and a defined failure mode where the reply contains the exact `align connect <source>` command. The 'only reads from the source' phrasing is consistent with readOnlyHint=false because the write target is the local graph, not the source.

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?

The action and scope are front-loaded in the first sentence, and each following sentence carries distinct information (trigger, behavior, failure mode, agent constraint). The token guidance is spread across two sentences, which is slightly more airtime than needed, but nothing is wasted.

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?

For a 2-parameter, non-destructive background import with no output schema, the description covers trigger, safety profile, credential handling, and failure recovery. It leaves the success reply shape and whether repeated backfills are deduplicated or re-fetch, which an agent guiding a user would benefit from.

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 coverage is 100%, with enums and the `since` format already documented in the schema, so the baseline is 3. The description adds only a soft hint ('the last year of GitHub PRs') and does not explain how `since` interacts with the per-source ceiling beyond what the schema states.

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?

"Import more history from a source the user has ALREADY connected (for example the last year of GitHub PRs) into the local graph on this machine" gives a specific verb (import history), a specific resource (connected source), and a concrete target (local graph). The example and the 'already connected' qualifier make it unmistakable against sibling read/query tools like align_ask or align_search.

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?

"Offer it when the user asks for older context than the graph holds" is an explicit trigger condition, and the description adds a when-not case (unconnected source or refused token → nothing starts). It never names an alternative sibling to route to for in-graph queries, so it falls short of a full when/when-not/alternatives set.

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

Deploy Server

Other Tools