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

Annotations already cover the mutation/safety profile (readOnly=false, destructive=false, idempotent=false, openWorld=false), and the description adds genuinely new behavior: text auto-shrinks to fit, image slots require an https PNG/JPG/GIF under 4 MB, omitted slots fall back to samples, and each call costs 1 credit. The billing and fallback-default disclosures are exactly the kind of context annotations cannot carry. Minor tension: accepting external https image URLs sits awkwardly with openWorldHint=false, though this is an indirect inference rather than a direct contradiction.

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?

Five short sentences, each carrying a distinct operational fact (output, text fitting, image constraints, default behavior, cost), with the outcome front-loaded. No filler or restatement of the name.

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, so the description is the only source for the return value, and it only says "a finished PNG" without stating whether that is a URL, base64 payload, or binary, nor any expiry/retrieval detail. Cost, defaults, and input constraints are well covered, but the response contract for a non-idempotent, credit-consuming call remains underspecified.

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 baseline is 3, but the description adds real meaning about the free-form modifications object: keys are slot names, values are text or image URLs, and an absent key preserves the template sample. It also constrains image value types and size, which the schema leaves as generic additionalProperties.

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?

"Fill a template's slots and get back a finished PNG" states a concrete action and output artifact, and the template/slot model plus PNG output implicitly separates it from render_chart, render_document and render_video. It never explicitly names or rules out a sibling, so differentiation is inferred rather than stated.

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?

Usage is implied rather than directed: the agent learns it needs a template id (schema says "from list_templates") and that omitted slots keep their sample, which tells it when this tool is applicable. There is no explicit when-to-use versus render_chart/render_document guidance and no stated prerequisites.

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