Skip to main content
Glama
sumithr

sumo-qa

by sumithr
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

sumo_qa_format_qa_scorecard

Read-onlyIdempotent

Generate a QA readiness scorecard from existing test and coverage evidence, then derive a clear merge or release recommendation based on risk and freshness.

Instructions

Compose a QA READINESS SCORECARD from already-produced evidence and DERIVE a readiness recommendation (issue #151). EVIDENCE SUMMARY, NOT a predictive quality score — it infers no risk, invents no numeric score, and the host can never assert "ready": the verdict is computed.

Common natural-language phrasings that map to this tool: "is this ready to merge/release", "give me a readiness scorecard", "summarise QA readiness", "release review summary".

Inputs are all optional and reuse the existing artifacts — nothing is re-defined here:

  • ledger_rows — the #144 risk-to-test rows (same shape as sumo_qa_format_risk_ledger); supplies risk coverage + blockers.

  • context_bundle — the #149 bundle (same shape as sumo_qa_format_context_bundle); supplies test/CI evidence freshness.

  • coverage / mutation — optional {..., freshness} signals; absent ⇒ reported as "not measured", never assumed passing, and never allowed to outweigh an uncovered high-impact risk.

  • scope — optional label (a PR title, a release name).

  • local_head_sha: the host's live local head. Flags a stale bundle when it differs from the bundle's head_sha. When the bundle names a head_sha and this is omitted, the bundle is UNVERIFIABLE and its fresh-passing facts cannot support ready (a distinct reason, not "stale"). A bundle with no head_sha keeps the partial contract.

Returns the four-state recommendation (ready / ready_with_accepted_ residuals / blocked / insufficient_evidence), is_ready (true only for the two ready states), the uncovered-blocker / residual counts, the stale-evidence and not-measured dimension lists, the rendered markdown, a one-line compact_summary to drop inline in short answers, and a JSON-able serialized snapshot a downstream report (#157) can render. Readiness is refused whenever a risk is an uncovered blocker or evidence is stale — that guarantee is structural, not advisory.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
scopeNo
coverageNo
mutationNo
ledger_rowsNo
max_reasonsNo
context_bundleNo
local_head_shaNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.48.0

TDQS

A4.5/5.0
Behavior5/5

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

The description goes well beyond the readOnly/idempotent annotations by detailing exact refusal conditions, the four-state recommendation, stale versus unverifiable evidence semantics, and the structural guarantee that readiness is refused for uncovered blockers or stale evidence. No contradictions with annotations are present.

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 description is well-structured with bullets and front-loaded purpose, but it is lengthy and contains some redundancy such as repeated emphasis on not being predictive or not assuming passing. Overall, the length is justified by the tool's complexity.

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 description thoroughly covers output fields, refusal conditions, and input semantics, which is especially important given the absence of an output schema. The lack of any mention of max_reasons and limited detail on the exact serialized snapshot shape prevent a perfect score.

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?

With 0% schema description coverage, the description compensates well by explaining scope, coverage, mutation, ledger_rows, context_bundle, and local_head_sha in meaningful detail. However, max_reasons is not described at all, leaving a notable gap in parameter understanding.

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 clearly states the tool's function: 'Compose a QA READINESS SCORECARD from already-produced evidence and DERIVE a readiness recommendation.' It uses specific verbs and distinguishes the output from related formatters by referencing distinct artifacts and downstream reports.

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?

The description provides natural-language phrasings and explains that inputs reuse existing artifacts, giving strong contextual guidance. However, it does not explicitly contrast this tool with sibling tools such as sumo_qa_generate_qa_report or sumo_qa_format_risk_ledger, leaving some inference required.

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