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

Annotations already declare destructive=true, idempotent=true, readOnly=false, and openWorld=false, so the safety profile is covered. The description adds genuinely useful ownership context ('Server owns chip layout, safezones, and exact export pixels'), telling the agent the server controls pixel-level layout. However it does not explain the create-vs-replace trigger, the role of idempotencyKey, or what clear_existing destroys.

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 tightly written sentences with no filler, and the operation plus its scope are front-loaded. Nothing is wasted, though the extreme brevity is part of the completeness problem rather than a virtue here.

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?

This is a complex mutation with 10 parameters, nested objects, and enum-driven visual kinds, and the description covers almost none of that surface. An output schema exists so return values needn't be explained, but the upsert trigger (project_id), clear_existing, idempotencyKey, and the required 'slides' structure are all undocumented.

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 description coverage is 0% across 10 parameters (project_id, clear_existing, style, locale, idempotencyKey, etc.), so the description carries the full burden and largely fails to. 'From a slide document' loosely gestures at the slides array and 'chip layout' at the style.chip object, but no parameter behavior, format, or required-vs-optional meaning is clarified.

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+resource ('Create or replace a carousel project from a slide document'), and 'create or replace' usefully signals upsert semantics. It does not name or distinguish itself from adjacent siblings like carousels_preview, carousels_clone, or carousels_patch_slide, so an agent must infer the boundary.

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 guidance on when to use this versus carousels_preview (validate first?), carousels_clone, or carousels_patch_slide (incremental edits). No prerequisites, no mention of when a replace is triggered vs a fresh create. The agent is left to infer routing from the verb alone.

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