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

Annotations cover readOnly, openWorld, and idempotent traits. The description adds valuable behavior beyond those flags: it fetches the page like a crawler, performs one fetch plus one render per call, returns a watermarked free inline image, makes a Jev design decision in about 100 ms, and has a preset fallback. No contradiction exists between the description and 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 front-loaded with the core action and dense with useful detail. Every sentence contributes relevant behavioral or usage information, though a few details (preset, size) are also present in the schema, making it slightly redundant rather than perfectly lean.

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 but a rich input schema, the description provides the key invocation context: one-call flow, no API key, page fetching behavior, override semantics, default size behavior, and fallback design. An agent has enough context to select and invoke this tool correctly without missing critical information.

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?

The schema already describes every parameter comprehensively, so the baseline is 3. The description adds extra semantic value by stating that 'any field you pass overrides what the page says' and that preset lets the caller choose the design instead of relying on Jev. This clarifies parameter precedence and intent beyond the 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?

The description states a specific action and resource: 'Make a social card for a page that already exists, in one call.' It also clarifies the crawler-like gathering of page metadata and names the sibling list_presets where relevant, so an agent can distinguish this from render_card and og_image_url.

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 explicitly says 'Use this first when the user gives a URL' and gives a concrete user utterance ('make an OG image for my latest post'). It also mentions preset and size as optional choices, but it does not explicitly rule out or contrast with sibling tools like render_card or og_image_url, so exclusions are left implied.

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