Coderbuds

Get Ai Adoption Tool

get-ai-adoption-tool

Read-onlyIdempotent

How much of this team's shipped work is AI-assisted, and what that work did once it shipped. Returns adoption rate (share of active contributors using AI), contribution intensity (share of lines changed), the AI-assisted PR rate, which AI tools were detected, detection confidence, and a delivery outcome split comparing AI-assisted merged PRs against the rest on lead time and size. Use it to answer "is AI actually in our SDLC yet" and "is it paying off" with the same call. Adoption alone is a pilot metric — the outcome split is what turns it into a KPI, and the result says plainly when the samples are too small to compare or when detection has not covered the period. Bot and dependabot PRs are excluded from the outcome comparison. Where a coding agent reported a change (first-party, via report-ai-usage), its report decides how that PR is counted. The attribution block lists those reports and grades what Coderbuds inferred from the same diffs against them — the error rate every unreported PR carries.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`period`	No	Reporting period. Defaults to rolling_30d.	rolling_30d
`repository`	No	Optional "owner/name" repository slug used to resolve which of your teams this call is about. It does not filter the metrics — they always cover the whole team.

Output Schema

TableJSON Schema

Name	Required	Description
`team`	Yes	Team name.
`tools`	Yes	Detected AI tools with counts and shares.
`period`	Yes	Human-readable period label.
`caveats`	Yes	What these numbers do and do not prove.
`adoption`	Yes	Share of active contributors who shipped AI-assisted PRs.
`headline`	Yes	One-line read of adoption, intensity, and the outcome split together.
`outcomes`	Yes	AI-assisted versus other merged PRs on lead time and size, with a comparable flag.
`detection`	Yes	Detection threshold and how much of the period has actually been analysed.
`intensity`	Yes	Share of lines changed that came from AI-assisted PRs.
`confidence`	Yes	Detection confidence distribution across AI-assisted PRs.
`attribution`	Yes	What coding agents reported about their own usage, and how often the inferred detector agreed with them.
`assisted_pull_requests`	Yes	Share of PRs that were AI-assisted.

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 11, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Beyond the readOnly/idempotent annotations, it discloses meaningful behavior: bot and dependabot PRs are excluded from the outcome comparison, first-party reports via report-ai-usage take precedence over inference, the attribution block lists reports and grades inferred error rates, and the result explicitly flags small samples or uncovered periods.

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 metric inventory is front-loaded and most sentences carry distinct information (metrics, usage framing, caveats, attribution semantics). It is on the verbose side with some density in the attribution sentence, but little is pure filler.

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?

With an output schema present, the description needn't explain return values, and it instead covers the interpretive caveats an agent needs (sample-size warnings, detection coverage gaps, bot exclusion, report precedence). This is complete for a read-only analytics tool.

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 only two parameters, both fully documented in the schema (including the subtle note that `repository` resolves the team but does not filter metrics). The description text adds no parameter-level detail beyond that, so the baseline 3 applies.

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?

The description names the exact resource (AI-assisted shipped work) and enumerates the specific metrics returned: adoption rate, contribution intensity, AI-assisted PR rate, detected tools, detection confidence, and a lead-time/size outcome split. It clearly separates this from sibling adoption tools like get-mcp-adoption-tool and get-agent-activity-tool by framing the scope as AI-in-SDLC plus delivery outcomes.

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?

It gives explicit intended questions ('is AI actually in our SDLC yet' and 'is it paying off') and notes the outcome split is what elevates a pilot metric to a KPI. However, it never names or excludes the closest siblings (e.g., get-mcp-adoption-tool) or states when NOT to use this tool versus them.

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

All Coderbuds tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?