add_icon_to_slide

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

Annotations are sparse (only title), so the description carries the behavioral disclosure burden. It reveals meaningful traits: the icon lives on the server, the deck stores the image once regardless of repeats, and non-square drawings are centered rather than stretched. These go beyond the schema and clarify what the tool will actually do. It could add permission or failure behavior, but the provided details are substantial for a simple add operation.

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 description is well organized: purpose statement, caveat about icon_id storage, then parameter definitions, then return note. Every sentence serves a purpose and no empty phrases exist. The structure front-loads the essential purpose and then gives just enough detail for successful use.

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?

Given the tool's moderate complexity, the output schema, and the sparse annotations, the description covers the full call cycle: where the icon_id comes from, how the slide index is referenced, how the icon will be rendered, and what will be returned. It provides enough context to call the tool confidently without needing to inspect other tools or documentation.

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?

The input schema has 0% description coverage, so the description alone must explain every parameter. It does so for all six: presentation_id, slide_index with 0-based clarity, left/top in inches, size with recommended ranges, and icon_id identity. The description also explains the semantic of non-square content fitting in the size box, which is valuable operational context.

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 clearly states a specific action and resource: 'Place an icon you rendered with render_svg_icon onto a slide.' It also distinguishes itself from importing external images by explicitly noting it takes the icon_id, not a DIAL file URL. This makes the tool's unique purpose immediately clear among many sibling content tools.

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?

The description provides strong context for when the tool should be used: after calling render_svg_icon, and it highlights the difference from DIAL URLs. It also gives helpful sizing guidance and slide-indexing conventions. However, it does not explicitly name sibling alternatives or provide a 'when not to use' condition beyond the DIAL caveat.

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