Set slide properties

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

Annotations cover safety (readOnlyHint=false, destructiveHint=false, idempotentHint=true), and the description adds behavioral detail beyond them: markdown subset support vs. literal headings/code/links with a warning, refusal-before-mutation when notes are unsupported, per-slide results, and the editor/scope caveat ('Editors: Slides only, unverified'). That is substantive disclosure the structured fields do not carry.

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?

Front-loaded with the two properties and their semantics, then the markdown caveats, guidance, failure mode, and sibling routing in that order. Every clause earns its place, though the second half is densely stacked into a single run-on paragraph rather than broken into shorter units.

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 mutation tool with no output schema, the description covers everything needed: what changes, markdown limitations, refusal behavior, result granularity ('per-slide results'), and which editor must be active. Acknowledging that the Slides-only restriction is 'unverified' is honest handling of uncertainty rather than a gap.

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 67%, and the description supplements it by explaining what `skipped` actually does ('left out of the presentation, kept in the deck'), how `speakerNotes` renders markdown, and that an empty string clears notes. It adds real meaning over the schema, though it does not touch `session` or the idempotency key (both already well documented in the schema).

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 the exact verb and resource ('per slide of a Figma Slides deck') and names the two properties it controls, `skipped` and `speakerNotes`, with their meanings. It is immediately distinguishable from siblings like figma_set_slide_transition or figma_set_fills.

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 adjacent concerns to alternatives — slide names to figma_rename_node, backgrounds to figma_set_fills, transitions to figma_set_slide_transition — and gives a when-to policy for notes ('only when asked or for a deck meant to be presented'). It also states the when-not condition (build without speaker notes support causes a refusal).

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