KitchenSink4PPT

Overview Schema Source Related Servers Discussions Admin

Find Text

find_text

Read-only

Locate any text in a PowerPoint deck and get exact slide, shape, and character positions for targeted edits or formatting updates.

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

A4.6/5.0

Behavior5/5

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

With readOnlyHint=true already present, the description adds substantial behavioral detail: regex is guarded against catastrophic backtracking, text matching is on displayed text rather than raw XML, count is always the true total, pagination includes a 'page' block with omitted count and next offset, and compact changes the output shape. No annotation contradiction.

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 every sentence carries signal: output contract, regex safety, encoding nuance, pagination, compact mode, graphics-pack pointer, and sibling routing. It is front-loaded with the core purpose and return format.

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?

The description is unusually complete for a read-only search tool: output schema exists, annotations cover safety, and pagination/regex/display semantics are explained. The main residual gap is the undocumented scope and include_notes parameters, which prevents a perfect completeness score.

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 description coverage is 0%, so the description must compensate. It does explain regex, compact, query escaping, and offset/pagination, but it leaves several parameters unexplained: scope, include_notes, limit, and file_path semantics. This is a meaningful gap for an 8-parameter tool.

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 names a specific verb and resource: 'Search the deck's text' and specifies exactly what is returned (slide index, shape id, paragraph index, character offsets). It also differentiates itself from get_text by stating 'Use this to locate text; to read it in order, use get_text' and explicitly links its output to format_text and apply_edits.

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 gives explicit routing guidance: use this to locate text, use get_text to read text in order, and notes formatting-aware replacement lives in the graphics pack via enable_tools(packs=['graphics']). This is clear when-to-use and alternative selection.

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