KitchenSink4PPT

Overview Schema Source Related Servers Score Discussions Admin

find_text

Read-only

Locate text in a PowerPoint deck and retrieve precise match addresses (slide, shape, paragraph, character offsets) for editing. Supports regex and returns all matches, with pagination details when results are large.

Instructions

Search the deck's text. Returns every match with slide index, shape id, paragraph index, and character offsets, exactly the addresses format_text (graphics pack) and apply_edits consume. regex=True treats query as a regular expression (guarded against catastrophic backtracking). Matches text as displayed, not raw XML, so search for & rather than &. count is always the true total; a "page" block gives the omitted count and next offset when more matched than the budget fits. compact=True returns matches as a fields header plus one array each. Formatting-aware replacement lives in the graphics pack: enable_tools(packs=['graphics']). Use this to locate text; to read it in order, use get_text.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No
`query`	Yes
`regex`	No
`scope`	No
`offset`	No
`compact`	No
`file_path`	Yes
`include_notes`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv1.2.1Sep 9, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / compact

Added value: +{
+  "default": false,
+  "type": "boolean"
+}

addedInput schema / properties / limit

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

addedInput schema / properties / offset

Added value: +{
+  "default": 0,
+  "type": "integer"
+}

First observedv1.0.0Aug 31, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only provide readOnlyHint=true, and the description adds substantial behavior beyond that: regex is guarded against catastrophic backtracking, matching is against displayed text rather than raw XML, count is always the true total, pagination exposes an omitted count and next offset, and compact changes the shape. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but free of filler; every clause adds operational information, and the first sentence front-loads the core purpose. Subsequent details are grouped by related behavior (regex safety, XML escaping, pagination, compact output, tool routing).

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?

With an output schema present, return-value details are covered structurally. The description covers matching semantics, address format, pagination, and routing to sibling tools. Minor gap: scope and include_notes parameters are not described, but the overall behavior is sufficiently complete for an agent to call the tool correctly for common cases.

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 description coverage is 0%, and the description compensates well by explaining regex=True, compact=True, limit/offset pagination via the 'page' block, and the meaning of budget. However, scope and include_notes are left unexplained, and file_path/query rely on context rather than explicit semantics, so it is not complete.

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?

Opens with a specific verb+resource: 'Search the deck's text.' It then defines the exact return shape (slide index, shape id, paragraph index, and character offsets) and ties it to sibling tools by naming the addresses format_text and apply_edits consume. This clearly distinguishes find_text from get_text, which reads text in order.

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?

Explicitly routes usage: 'Use this to locate text; to read it in order, use get_text.' It also directs formatting-aware replacement to the graphics pack via enable_tools(packs=['graphics']), and notes apply_edits consumes its output, so an agent knows how this tool fits into a workflow.

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