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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so 'Read-only.' is pure repetition. The one genuine addition is 'Unsaved derived formats are absent,' which tells the agent results are filtered to persisted formats — useful, but no detail on pagination, ordering, or behavior when parameters are omitted.

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?

Three short sentences, front-loaded with what is returned and what is excluded. The only wasted line is 'Read-only.', which restates an annotation verbatim.

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?

An output schema exists so return structure needn't be explained, and the description still sketches the payload (layouts, variant metadata, primary format, available languages). Adequate for a zero-required-parameter read tool, with minor gaps around default behavior when language or variantId is omitted.

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 75% and the language, projectId and generationId descriptions are rich, so the schema does most of the work. The description reinforces that results are per-language and include variant metadata, but variantId remains undocumented in both places and no param syntax is added beyond 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 a specific verb and resource ('Returns saved social-graphics layouts and variant metadata'), and scopes it to one language while naming the included fields (primary format, available languages). An agent can distinguish it from mutating siblings like save_graphics or render_graphics, though it never explicitly names get_graphics_format or list_variants as the alternatives.

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 only implied: 'saved' and 'Unsaved derived formats are absent' signal this reads persisted state rather than rendering. There is no explicit when-to-use or when-not-to-use guidance, and the routing hints (list_graphics_translations, translate_graphics) live in the schema's language description, not in the tool description.

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