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

Beyond the readOnlyHint annotation, the description discloses that it renders nothing and spends no draft or credit, which is a significant behavioral detail. It also details the comprehensive output (template, fields, defaults, missing required, image sizes, brand kits, page/orientation/footer, saved templates, free drafts left, unlock cost, ready). This adds substantial context about what the agent can expect without contradicting the annotations.

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 description is a single, dense run-on sentence. It is front-loaded with the purpose and then lists outputs in a long clause. While it packs a lot of useful information, its structure could be improved by breaking it into multiple sentences for clarity. It is not concise, but given the complexity of the tool, the length is somewhat justified. Still, the structure is a minor detractor.

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?

Given the tool has 15 parameters and no output schema, the description does a good job of describing the return value comprehensively. It lists all the key output elements (template, fields, defaults, missing required, sizes, brand kits, page/orientation/footer, saved templates, drafts left, unlock cost, ready). It also provides usage context and the condition for same-turn generation. However, it lacks details on error handling or edge cases, which keeps it from being fully complete.

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 only 40% schema description coverage, the description needs to compensate for undocumented parameters. It only explains the 'kind' parameter (og_image for image, email or pdf for document) and mentions passing 'whatever the user has said so far', but does not explain other parameters like page, align, props, header, markdown, appearance, footer_text, page_numbers. The schema has enums for some but lacks descriptions for most, so the description does not adequately cover the parameter space.

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?

The description clearly states the tool's purpose: to plan a generation without rendering or spending resources. It explicitly names the tool's output (template, fields, defaults, missing required, etc.) and differentiates it from sibling generation tools by instructing to call it before generate_og_image, generate_email, or generate_pdf. This makes the purpose unambiguous and distinct from siblings.

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 description provides explicit usage guidance: 'Call it once before generate_og_image, generate_email or generate_pdf, then generate in the same turn unless one open choice would change the result.' This tells the agent when to use it, the order relative to generation tools, and the condition for generating in the same turn. It also implies not to call after generation, offering clear when-to and when-not-to guidance.

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