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

Annotations only cover safety/idempotency; the description adds what the annotations cannot: the model picks the shape, icons and colours and infers missing content, so output is generative and non-deterministic (consistent with idempotentHint=false). It discloses the return payload (editable AI Flowchart link plus a PNG) and, importantly, the cost — "Uses 1 AI credit" — which is operationally decisive.

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?

The verb-and-artifact statement is front-loaded, and the credit cost and return values are placed at the end where they belong. It is a single dense block with some intentional redundancy in the synonym list ("infographic, a visual, a one-page graphic, a slide graphic") that serves trigger matching rather than padding, though it reads as a run-on.

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?

There is no output schema, and the description compensates by naming both return artifacts and their editable/export capabilities. With cost, generation behaviour, input routes and sibling exclusion all covered, an agent has everything needed to select and invoke it 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 coverage is 100%, so the baseline is 3, but the description adds the either/or semantics between the two inputs (describe the topic, or pass a prior diagram link to convert it) rather than restating field docs. The schema already carries "Leave out only when diagram is given", so the added value is modest but real.

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?

"Make a designed infographic of a topic" gives a specific verb and artifact, then enumerates the concrete shape families (steps, cycle, timeline, funnel, 2×2 matrix, architecture layers) so the agent knows exactly what class of output this produces. It explicitly distinguishes itself from the sibling box-and-arrow diagram tool (create_diagram), so no schema inspection is needed to tell them apart.

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?

The trigger conditions are spelled out with user vocabulary ("infographic, a visual, a one-page graphic or a slide graphic of a process, plan, architecture, comparison, timeline or concept") and an explicit exclusion ("rather than a box-and-arrow diagram"). It also states the two input routes — a topic description, or a link to a diagram made earlier in the chat — which is the decision an agent actually faces.

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