Skip to main content
Glama
wkqco33
by wkqco33

ppt_add_slide

Add a new slide to a PowerPoint presentation with a title, body content, and layout selection. Optionally create a backup before modifying the file.

Instructions

Add a new slide to a PowerPoint presentation (.pptx).

Args:
    file_path: Path to the PowerPoint file.
    title: Title for the slide.
    content: Optional content text for the body placeholder.
    layout_idx: Slide layout index (0=Title Slide, 1=Title and Content). Default 1.
    backup: If True, create a backup of the original file before modifying.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYes
backupNo
contentNo
file_pathYes
layout_idxNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden of disclosing side effects. It mentions the backup parameter ('create a backup of the original file before modifying'), which implies the tool modifies the file. However, it does not state whether it appends to the end, whether the file must exist, or any error conditions, leaving gaps in behavioral disclosure.

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 structured as a concise docstring with an Args list, front-loading the purpose. Each parameter gets a single line with no fluff. It is efficient and easy to scan, though the multi-line format is slightly longer than strictly necessary.

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?

Given the output schema exists, the description needn't explain return values. It covers all parameters and the overall purpose. It omits preconditions like file existence and append behavior, but for an add-slide operation these are largely implied. The inclusion of backup and layout_idx adds sufficient context for a typical call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage, so the description must compensate. It explains every parameter: file_path (path), title, content (optional body placeholder text), layout_idx (with specific meanings for 0 and 1), and backup (backup behavior). This adds meaning far beyond the raw schema types and is essential for correct invocation.

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 'Add a new slide to a PowerPoint presentation (.pptx)' with a specific verb (add) and resource (slide). It clearly differentiates from sibling add tools (ppt_add_table, ppt_add_chart, ppt_add_flowchart) and from ppt_create_presentation, so an agent can correctly identify what this tool does.

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

Usage Guidelines3/5

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

The description implies usage by listing layout options (Title Slide vs Title and Content) but does not explicitly mention when to choose this tool over alternatives like ppt_add_table or ppt_update_slide_text. There is no guidance on exclusions or conditions, so it relies on the tool name for selection context.

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