Skip to main content
Glama

SlideForge

by dev.slideforge

Plan a Slide - Form + Variant Candidates

plan_slide
Read-onlyIdempotent

Plan a PowerPoint slide before rendering (free): send a short brief, get ranked candidates + a separated verdict — route (which slide: selected|needs_confirmation|ambiguous), input (can it render: ready|extractable_from_brief|needs_structured_data) and next_action. Free (one embedding). Then call create_slide with the chosen form(+variant). route.confidence: calibrated = measured P(route correct) with label high/medium/low cut on it; retrieval_score/retrieval_margin = the raw family-aggregated classifier values (not probabilities; margin can be negative when families contest); source = classifier | structural_router (LLM-rescued). candidate_margin on the top candidate = literal gap between the two shown scores.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topNo
briefYes
escalateNoDefault true: on a low-confidence route the plan runs the SAME LLM rescue create_slide would (small COGS on that tail only), so plan and create always agree. Set false for a classifier-only, fully free plan (response then flags will_escalate + create_slide_behavior).
variant_policyNoproduction_safe: if the top routed variant is draft/beta, the family's demo-safe sibling leads and route reports both best_semantic and best_production_safe.

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already indicate readOnly/idempotent, and the description adds significant behavioral context: route.confidence is a calibrated probability, retrieval scores are raw classifier values, and escalate ensures plan/create agreement. This goes far beyond the annotation hints.

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 dense but well-structured: it front-loads the purpose, then explains response fields and the relationship to create_slide. No wasted sentences, though the level of detail is high.

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?

No output schema exists, but the description thoroughly documents the response format (route, input, next_action, confidence, scores, source) and the escalate behavior. It also connects to the larger workflow, making the tool's usage complete despite the missing output schema.

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 covers escalate and variant_policy but omits descriptions for brief and top. The description partially compensates by calling the brief 'short' and implying it is a slide brief, but it never explains what 'top' controls (likely number of candidates). At 50% coverage, the gap is not fully bridged.

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 states a specific action: 'Plan a PowerPoint slide before rendering' and details the output (ranked candidates, route/input/next_action). It distinguishes itself from the sibling create_slide by explicitly instructing to call create_slide afterwards.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear when-to-use guidance ('before rendering'), an explicit next step ('Then call create_slide'), and explains the free tier ('Free (one embedding)') and escalate behavior. This effectively tells the agent when to invoke plan_slide versus the alternative.

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

All SlideForge toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.6/5.0
Disambiguation5/5

Each tool maps to a distinct phase or responsibility: browse_catalog for exploration, plan_slide for pre-render planning, create_slide/create_deck for single vs multi-slide generation, upload_asset for asset intake, translate_deck for translation, and manage_account for account/job operations. No two tools appear to do the same thing.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with lowercase and underscores (browse_catalog, create_deck, create_slide, manage_account, plan_slide, translate_deck, upload_asset). This uniform convention makes the set predictable and easy to navigate.

Tool Count5/5

Seven tools provide a well-scoped coverage of the PowerPoint generation workflow—from browsing and planning to creating, asset management, translation, and account control—without unnecessary duplication or bloat.

Completeness5/5

The tool surface covers the full lifecycle: exploration (browse_catalog), planning (plan_slide), single/multi-slide creation (create_slide/create_deck), asset upload/generation (upload_asset), translation (translate_deck), and account/job management including deletion and webhooks (manage_account). No obvious dead ends or missing operations.

Resources