Skip to main content
Glama

Creative ideation session — Atom

Creative ideation session

creative_ideation_session
Read-onlyIdempotent

Submits a creative-ideation session record (brief and preparation, capture and generation, divergence methods, idea pool, selection criteria, shortlist and outcome) and returns a deterministic SESSION_COMPLETE / SESSION_NOT_COMPLETE / INSUFFICIENT_EVIDENCE verdict across six sections, including computed volume-vs-target, dedup-arithmetic, shortlist-within-pool and method-vocabulary checks, with per-check evidence. Audits the declared session record; it generates no ideas and judges none.

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": "creative_ideation_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
briefNoBrief evidence.
captureNoCapture evidence.
outcomeNoOutcome and ship evidence.
idea_poolNoIdea-pool evidence (declared counts).
selectionNoSelection-criteria evidence.
shortlistNoShortlist evidence.
divergenceNoDivergence-methods evidence.
generationNoGeneration evidence.
preparationNoPreparation evidence.
session_titleNoSession title.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the read-only and idempotent annotations, the description names the deterministic verdict categories, six-section audit, computed volume/dedup/shortlist/method checks, and per-check evidence. It also clarifies the non-generative, non-judgmental behavior of the tool.

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 uses two dense sentences, front-loaded with purpose and then boundary. The parenthetical field list is long but each clause carries information; it could be split for readability but contains no filler.

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 ten-parameter, nested-object audit tool with no output schema, the description explains the purpose, verdict categories, and check families adequately. It leaves detailed verdict criteria and per-field evidence requirements implicit, but gives enough for selection and invocation.

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%, so the schema already defines all ten fields. The description groups several fields into the session record and signals the evidence sections, but it adds little about expected object contents or validation semantics beyond the field names.

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 opens with a concrete verb and resource ('Submits a creative-ideation session record'), enumerates the record sections, and states the exact verdict outputs. It also explicitly distinguishes the tool from idea generation and judgment, making its scope identifiable.

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 establishes the context as auditing a declared session record and explicitly rules out idea generation and judging, giving a usable when/when-not boundary. It does not provide more detailed invocation guidance or alternatives, but the audit context is clear.

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.