Skip to main content
Glama

Tech stack decision memo — Atom

Tech stack decision memo

tech_stack_decision_memo
Read-onlyIdempotent

Submits a tech-stack decision memo record (context and constraints, declared candidate rows and boring-technology declarations, evaluation criteria rows and evidence, total-cost and operability declarations, decision and rationale, reversibility and exit declarations, red lines) and returns a deterministic TECH_STACK_DECISION_SOUND / TECH_STACK_DECISION_NOT_SOUND / INSUFFICIENT_EVIDENCE verdict across seven sections, including computed criterion-reference, weighted-score recomputation and decision-candidate consistency checks over the declared rows, with per-check evidence. Audits the declared memo record only; it recommends no stack, picks no stack and ranks no candidate.

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": "tech_stack_decision_memo"
  }
}

Input Schema

NameRequiredDescriptionDefault
tcoNoTco evidence.
contextNoContext evidence.
criteriaNoCriteria evidence.
decisionNoDecision evidence.
red_linesNoRed lines evidence.
candidatesNoCandidates evidence.
evaluationNoEvaluation evidence.
memo_titleNoMemo under review.
reversibilityNoReversibility evidence.
candidate_workNoCandidate work evidence.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real value beyond them: the three possible verdicts, the seven-section structure, and the fact that criterion-reference, weighted-score recomputation and decision-candidate consistency checks are computed over the declared rows with per-check evidence. This discloses determinism and the audit-only scope. The only mild ambiguity is 'Submits', which could be read as a write, though 'audits the declared memo record only' resolves it toward evaluation.

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 verb and scope are front-loaded, but the first sentence is a long run-on that lists seven section contents inline, and the closing triple ('recommends no stack, picks no stack and ranks no candidate') restates one idea three ways. The content is dense and mostly earns its place, yet it would read faster as a short structure list than as a comma-chained sentence.

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 10-parameter tool with nested objects and no output schema, the description carries the important load: it names the verdict set, the seven-section basis, and the computed checks with per-check evidence, which is what an agent needs to interpret a result. It openly points to SERVICE.md for the field table, which is a reasonable deflection rather than a silent gap.

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?

Schema coverage is 100%, so the baseline is 3, but the schema's own descriptions are near-tautological ('Tco evidence.', 'Criteria evidence.'). The description compensates by enumerating what each section must contain — context and constraints, candidate rows and boring-technology declarations, criteria rows and evidence, TCO and operability declarations, decision and rationale, reversibility and exit declarations, red lines. It does not clarify memo_title or candidate_work, and defers the field table to SERVICE.md.

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 uses a specific verb and resource ('Submits a tech-stack decision memo record') and then states the exact output artifact: a deterministic TECH_STACK_DECISION_SOUND / NOT_SOUND / INSUFFICIENT_EVIDENCE verdict. It also draws a hard boundary ('Audits the declared memo record only; it recommends no stack, picks no stack and ranks no candidate'), so an agent cannot mistake it for a stack-recommendation tool.

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 final sentence gives an explicit negative-use rule: this tool audits a declared memo and does not recommend, pick, or rank. That tells an agent what this tool will not do, which is the main mis-selection risk. There is no positive when-to-use framing or named alternative, but no siblings are supplied against which one could be named.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.