design.search_by_image

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

Annotations already establish readOnly/idempotent/closed-world, so safety is covered. The description then adds genuinely useful behavioral context beyond that: DINOv2 visual embeddings, HNSW nearest-neighbor retrieval, and the exact RRF fusion weighting (40/30/30) when a query is present, which tells the agent how results are ranked and why hybrid results may differ.

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?

Four sentences, well front-loaded: purpose first, accepted inputs second, mechanism third, optional-mode fourth. No filler. Slightly over-indexed on implementation internals (DINOv2/HNSW) that an agent does not strictly need to call it.

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?

Parameters are fully documented via schema and safety via annotations, but there is no output schema and the description says nothing about what a result looks like (sections, similarity scores, ordering, count). For a search tool whose output shape is undefined elsewhere, that is a notable remaining 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 100%, so the baseline is 3; the description earns extra credit by explaining the semantic effect of the 'query' parameter (it switches the whole search into a 3-source RRF fusion rather than a pure visual lookup), which the schema text alone does not convey.

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: searching design sections visually similar to a supplied image. It distinguishes itself from the other *search* siblings (layout.search, motion.search, narrative.search, background.search) by naming the modality (image) and the target resource (design sections) rather than sites or parts.

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?

Explains the two input modes (Base64 or HTTPS URL) and, critically, the condition that switches behavior: an optional text query triggers the RRF hybrid search. That is clear context for mode selection. It stops short of stating when to prefer design.similar_site or search.unified instead, so no explicit exclusions.

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