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

Annotations cover safety (readOnlyHint, openWorldHint), and the description adds real context beyond them: the catalogue is account-filtered, a 'scenes:read' permission is required, and generation is out of scope for this tool. Missing details like pagination or result shape, but the added auth and scoping facts are substantive.

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 compact sentences, front-loaded with what the tool does and followed by usage and permission. No filler, though the middle sentence is slightly redundant with the opening 'filtered to the ones that suit this account'.

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?

With no output schema, the description should hint at what comes back; it loosely says it 'finds the scenes that fit' but does not characterize the returned objects. Given a simple two-parameter, zero-required read tool, the definition is otherwise sufficient to invoke correctly.

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 both parameters (q, limit) are already fully documented in the schema, making 3 the baseline. The description adds only mild semantic color — that q is a natural-language 'what the person is after' free-text query — without format or syntax 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: 'Searches CMeIn's scene catalogue', quantified as 'over 4,500 settings' and scoped to 'filtered to the ones that suit this account'. It is clear and concrete, but never names or contrasts with the obvious sibling find_video, so sibling differentiation is left to inference.

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 usage context: 'Use it to recommend one' and 'describe what the person is after and it finds the scenes that fit'. It also draws a useful boundary ('Generating the photo itself is done in the app'). It stops short of explicit when-not guidance or pointing at find_video for video needs.

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