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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavioural facts beyond them: similarity is precomputed, results are filtered to published and reviewed scenes only, and signed images attach to the first 12 results. Gaps remain on pagination behaviour and what exclude_brand does.

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 short sentences, front-loaded with what the tool returns, no filler or repetition of the title.

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 shape need not be explained, and the catalogue filtering is covered. But for a 6-parameter tool with zero required parameters, the agent is left without knowing whether to supply `id` or `scene_id` or how to paginate, which is a material omission.

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 only 17% (only `images` is documented), so the description must compensate and does so only partially: it explains the 12-result default-adjacent image behaviour. It says nothing about `cursor`, `limit` up to 50, `exclude_brand`, or the ambiguous pair of `id` and `scene_id` (identical patterns, neither required).

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-and-resource: returns scenes that look like a chosen scene, sourced from precomputed visual similarity and restricted to the published/reviewed catalogue. That clearly separates it from text-oriented siblings like search_scenes or search_by_moment, though no sibling is named explicitly.

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?

'Scenes that look like a chosen one' implies the trigger (you have a scene and want visually similar ones), but there are no explicit when-to-use/when-not rules and no named alternatives (pattern_search, compare_to_reference, search_scenes) to route between.

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