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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), and the description adds operationally significant facts the annotations cannot convey: the model runs locally with no API key, first use downloads ~350 MB, and similarity_score is only comparable within a single query. The last point is a real caveat about result interpretation that an agent would otherwise get wrong.

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 core action and mechanism, then layers on the practical details an agent needs. Four dense sentences with little waste, though the parenthetical '2 of the 30 images' statistic is more color than load-bearing.

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, and the description compensates by explaining the one return field that matters (similarity_score and its within-query-only scope), plus cold-start latency and offline operation. For a three-parameter read tool with full annotation coverage, nothing needed to call it correctly is missing.

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 100%, so query, limit, and country are all already documented, and the description adds only illustrative query examples rather than new semantics. It says nothing about limit defaults or country filtering behavior, so the schema does the heavy lifting and baseline 3 applies.

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 ('Find photographs by describing what they SHOW') and immediately qualifies the retrieval mechanism as cross-modal against an image embedding rather than a caption. That distinction is exactly what separates it from keyword-based siblings like search_images or search_audiovisual, even without naming them.

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?

Gives clear context for when this is the right tool: visual-content queries, in any language, and it explains why it succeeds where caption-based search would fail (only 2 of 30 images have captions). It does not explicitly name an alternative or state exclusions (e.g., 'use search_images for metadata filters'), so it stops short of a 5.

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