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

Goes well beyond the annotations by disclosing quota consumption (monthly AI-image limit), auth requirements (needs a connected account, edit_token for drafts), the server-side rendering model (no upload needed), and the side effect of overwriting the event's cover. Annotations only tell the agent this is a non-readonly, non-destructive mutation; the description supplies the operational consequences.

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 payload-free rendering guarantee, and every clause carries information (quota, side effect, draft iteration, auth). It is dense and em-dash heavy, but not padded or repetitive.

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 5-param mutation tool with no annotations covering behavior and no output schema, the description covers the essentials: inputs, auth, quota, and the state change. It does not say what comes back (image URL, confirmation) or what happens on failure/limit exhaustion, which are the remaining gaps.

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?

With 0% schema coverage, the description must carry the params and largely does: prompt is described by what to put in it (vibe, palette, imagery, energy), event_id vs draft_id + edit_token are explained including their pairing and purpose. include_title is only alluded to via "the event's name becomes the flyer's hero title by default," without confirming it is the toggle or its default.

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 (generate) and a concrete resource (a brand-new cover image / finished event flyer) plus the input modality (text prompt). The word "brand-new" implicitly separates it from refine_event_cover and set_event_image, but neither sibling is named, so the agent has to infer the boundary.

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?

Clearly states the two usage paths: a live event via event_id, or an unclaimed draft via draft_id + edit_token, and explains that draft covers carry over when published. It omits the obvious alternative for iterating on an already-generated cover (refine_event_cover), leaving that routing decision to inference.

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