preview_deck_generation

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

With no annotations, the description carries the full burden. It usefully discloses that no API call is made and that it returns a pending image count and an approval token, which suggests a dry-run gated by approval. But it is ambiguous whether 'write every final prompt' mutates stored state or is purely in-memory, and no permission or idempotency behavior is described.

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?

Two short sentences with no filler, and the action and its outputs are front-loaded before the 'No API call' qualifier. Slight terseness borders on under-specification rather than waste.

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?

Because there is no output schema, the description rightly reports what is returned (pending image count, approval token). It is nevertheless incomplete for a workflow-gating tool: the meaning of the sole input and the relationship to approve_plan / generate_deck_images are left unstated.

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 0% for the single required parameter 'presentation', so the description must compensate and does not. An agent cannot tell from either source whether 'presentation' is an ID, a title, a slug, or an inline document structure.

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 names a concrete action ('write every final prompt') and its outputs (pending image count, approval token), which is more specific than the tool name alone. However, it never states the resource it operates on or how it differs from close siblings like generate_deck_images or preview_slide_prompt, so an agent must infer that this is a pre-generation dry run.

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?

'No API call' hints this is a non-executing preview step, which implies it should precede generate_deck_images, but the relationship is never made explicit. There is no when-to-use / when-not-to-use statement and no mention of any prerequisite (e.g., an approved plan or submitted briefs).

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