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

Annotations cover the safety profile (readOnly=false, destructive=false), and the description adds substantial context beyond them: synchronous/instant execution, a flat cost of 2 credits regardless of format count, and that returned signed JPEG links expire after 24 h. These are exactly the facts an agent needs before committing a paid write call.

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 verb and resource, then layers source options, formats, cost and return value in a dense but readable block; nothing is wasted. It reads as a run-on sentence with fragment clauses, which costs a little clarity.

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 tool with no output schema, the description covers everything an agent needs: the input alternatives, the output form (signed JPEG links), their lifetime, the cost, and that execution is instant. Nothing material is left unstated.

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 the enum values, defaults and size mapping are already fully documented in the schema. The description largely restates format dimensions and source-id meaning rather than adding new semantics, so it sits at the baseline for a fully-documented 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 (make) and resource (cover/thumbnail JPEG) and immediately scopes it: a frame from a finished project (project_id) or an uploaded image/video (upload_id) with a headline. This distinguishes it from siblings like create_short, create_post_kit and create_compilation without the agent opening a schema.

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 ingestion paths (project_id vs upload_id) and the available output formats, so usage is clearly implied. However, it never names an alternative tool or a when-not condition, and gives no guidance on which source to prefer or what to do when neither id is available.

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