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

Annotations already establish read-only, idempotent, non-destructive behavior, yet the description still adds real substance: hidden slides are silently skipped by default, charts/diagrams are counted rather than omitted silently, and the tool errors on picture-only decks. That error condition in particular prevents wasted retries. It doesn't cover limits (50 MB / 500 slides live only in the schema), but the added behavioral context is genuine.

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

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

A single dense paragraph with no filler; the core action leads, followed by format, filtering, exclusions, and failure mode in a logical order. It is on the long side for a ten-second read, and could be broken into short lines for scannability, but no sentence is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does the work of describing the return shape (txt/md text, or json with slides/title/paragraphs/tables/notes) and the one failure mode. Size and slide-count limits are left entirely to the schema, and there's no pagination hint for 500-slide decks, so it stops just short of fully self-sufficient.

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

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

Schema coverage is 100%, so baseline is 3; the description goes past it by explaining what each switch implies semantically — default txt, json returning a structured slide model, and the default-false behavior of includeNotes/includeHidden. It reinforces rather than duplicates, which is the useful case.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Get the text') and a precisely scoped resource ('every slide in a PowerPoint (.pptx)'), then enumerates exactly what is extracted: titles, bullets with levels, tables, optional notes. An agent can immediately tell this is the text-extraction sibling of pptx_extract_charts / pptx_extract_images / pptx_extract_notes without opening a schema.

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

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

Gives concrete selection cues: use json 'easiest to process', includeHidden controls hidden slides, includeNotes pulls speaker notes, and charts/diagrams are explicitly out of scope. What's missing is naming the actual alternatives (pptx_extract_charts, pptx_extract_notes) so the agent doesn't have to infer the routing from the exclusion sentence.

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