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

Annotations already declare readOnly/openWorld=false/non-destructive, so safety is covered. The description adds genuinely non-obvious behavior: an extra return field galleryEmbedUrl that is an iframe-embeddable gallery valid for only 1 hour, which affects how an agent should time its handoff to the user. It does not mention pagination or truncation behavior for the limit parameter.

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 sentences, front-loaded with the primary purpose, followed by the side-effect-like gallery return. Dense but every clause carries information; the parenthetical about the iframe and 1-hour validity is well placed.

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?

No output schema exists, so the description's explanation of galleryEmbedUrl and its expiry is necessary and present. For a zero-required-parameter read-only lister that is nearly complete; only the limit/pagination semantics and default result size are left unaddressed.

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% — light, query, and family are described inline, only limit is undocumented. The description adds no parameter meaning of its own beyond the schema, so the baseline of 3 applies; it neither compensates for the limit gap nor clarifies how filters combine (e.g. query AND family).

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?

Specific verb+resource ("Lister les modèles visuels des présentations") and it immediately states what the returned identifier is for — passing it to create_presentation or set_presentation_theme. This ties the tool to its consumer siblings, so an agent can distinguish it from list_presentations or set_presentation_theme without inspecting schemas.

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?

Usage is clear: fetch themes when you need a theme identifier or want the user to pick one via the embeddable gallery. The alternative path (call this, then set_presentation_theme) is explicit. It lacks an explicit when-not clause, e.g. when an existing presentation already has a theme, but the context is sufficient to act.

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