slides_type

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

With no annotations, the description carries the full burden and does so: it discloses that replace mode is destructive ('clears the shape first'), that long text is chunked into ~90-second segments each verified against the saved deck, and that the call blocks until typing completes. It also notes typos are simulated and then fixed with Backspace, so the agent knows the intermediate state is intentional.

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?

The sentence is front-loaded with the core purpose and the destructive 'replace clears first' caveat appears early. It is a single dense run-on that packs mode, formatting, chunking, and return behavior together, which costs some scannability but wastes no content.

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?

For a 12-parameter tool with no output schema and no annotations, the description covers timing, verification, blocking behavior, and destructive semantics well. Remaining gaps are failure handling (what happens if verification fails mid-chunk) and whether anything is returned, though the latter matters less for a typing action.

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 92%, so the schema already documents wpm, seed, typos, pauses, profile, account, markdown, and shape. The description adds only marginal semantic value beyond that — the markdown implementation detail (bullets/numbers become real lists; bold and italic toggled via Cmd+B/I) is genuinely new, but other parameters are not elaborated on.

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?

The description opens with a specific verb and resource ('Type text into a slide') and immediately qualifies the distinctive mechanism: keystroke-by-keystroke human-paced input rather than a bulk write. It enumerates the targets (title, subtitle, body, numbered shape, speaker notes), which makes it distinguishable from the sibling write/edit tools without opening their schemas.

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?

Mode semantics are spelled out ('replace (default) clears the shape first; append adds paragraphs after its text'), but the description never states when an agent should pick this tool over slides_write, slides_replace, or slides_edit. The human-typing framing implies a demo/recording use case, but that inference is left to the reader.

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