Get Page Images

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

Annotations provide readOnlyHint=true, and the description aligns with this by describing a retrieval operation. The description adds valuable behavioral context beyond annotations: it specifies image type filtering (PNG, JPEG, etc.), fallback MIME type detection, size limitations (skips >50 MB images), error handling (error entry in summary), and the return format (list with summary + ImageContent). This significantly enhances the agent's understanding of the tool's behavior.

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 efficiently structured and front-loaded: the first sentence states the core purpose, followed by key details (filtering, return format, limitations). Every sentence adds essential information—image types, MIME fallback, size limits, error handling, and return structure—with zero wasted words. The Args and Returns sections are clearly separated for readability.

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's moderate complexity (one parameter, read-only operation), the description is complete. It covers purpose, usage, behavioral details (filtering, size limits, error handling), and return format. With annotations indicating read-only and no output schema, the description fully compensates by explaining the return structure (list with summary + ImageContent), making it sufficient for an agent to use the tool effectively.

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 description coverage is 100%, with the parameter 'content_id' well-documented in the schema as 'The ID of the Confluence page or blog post'. The description adds minimal value beyond this, only mentioning 'content_id' in the Args section without additional context. Since the schema already fully describes the parameter, the baseline score of 3 is appropriate.

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 specific action ('Get all images attached to a Confluence page') and resource ('as inline image content'), distinguishing it from sibling tools like 'confluence_get_attachments' (which gets all attachments) and 'confluence_download_attachment' (which downloads a single attachment). It precisely defines the scope as filtering to images only and returning base64-encoded content.

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 clear context about when to use this tool: for retrieving images from a Confluence page as base64-encoded content, filtering out non-image attachments. It implicitly distinguishes from siblings by focusing on images only, though it doesn't explicitly name alternatives like 'confluence_get_attachments' for all attachments or specify when not to use it.

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