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

Annotations already declare readOnly=false, destructive=false, idempotent=false, so the agent knows this is a non-destructive, non-idempotent writer. The description adds real value beyond that with the 64-tile ceiling, playing-video support and timed transitions toward a hero tile, but says nothing about how the collage is placed relative to the required start/end range, whether prior collages are replaced, or what happens on repeat calls.

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 tightly packed sentences that front-load the creation action and follow with capabilities and limits; nearly every clause carries information. Slightly more density could be traded for clarity given the number of undocumented parameters named nowhere.

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?

For a 13-parameter, 4-required creation tool with no output schema and near-zero schema documentation, this description is too thin. It omits timeline placement semantics, timing/animation parameters, and the meaning of most inputs, so an agent cannot call it confidently beyond kind/tiles/start/project_id.

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 8% (only project_id is documented), so the description must carry the burden and largely does not. It hints at 'tiles' count and a 'hero' tile, but leaves layout, backdrop, title, kicker, at, end, id and collapse_at entirely unexplained, leaving 13 parameters mostly opaque.

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 ('Creates') and three concrete output forms (mosaic, scrolling thumbnail wall, flatlay) that map directly onto the 'kind' enum values. The resource and its composition source ('specified project footage and images') are clear, though the description never names or contrasts any sibling such as compose_panels or add_element.

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?

There is no statement of when to choose add_collage over the many other add_* visual tools, and no exclusions or prerequisites beyond the implicit need for existing project media. The only usage-shaped information is the 'up to 64 tiles' cap, which is a constraint rather than routing guidance.

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