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

With no annotations, the description carries the full burden and does: 50-per-call/slide caps, Pro gating, atomic all-or-none semantics, default placement and fitting behavior, coordinate clamps to the slide, the behind-layer caveat where solid fills hide the object, and the returned payload. It also lists named error codes and tells the agent to re-read with get_template and retry on conflict.

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?

Dense but front-loaded: limits and the sibling comparison come first, then item shape, coordinates, colors, assets, layering, atomicity, return value and errors. It is a long paragraph, and splitting the error list from the behavioral prose would aid scanning, 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?

Although there is no output schema, the description states what is returned ('the slide's objects with their ids and the new version'), and it covers rate/size limits, atomicity, prerequisites, defaults and error recovery for a four-parameter mutation with nested item objects. Nothing an agent needs to call it correctly is missing.

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 75%, and the description still adds meaning beyond it: position and size are optional with stated defaults ('a text box lands near the middle, an image is centered and fitted'), colors are theme tokens rather than hex, images must come from list_media ids, and behind:true is explained along with the solid-fill caveat. It does not cover expected_version, which the schema handles.

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 and resource ('Add text boxes and images on top of one slide of a saved template') and immediately bounds the scope ('it never touches slots, other slides or other objects'), which separates it from update_template and update_objects 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?

Explicitly routes away from update_template for placing objects and states the Pro-account prerequisite. It does not distinguish itself from update_objects or remove_objects, so the add-vs-modify choice is left to inference.

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