render_report

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

With no annotations, the description carries full burden and excels: it discloses the detailed JSON structure (resolved box, text, overflow/clip flags, data_source, computed colours, board background/theme) and highlights an edge case (widget cells render into shadow DOM so their text may be empty). This is rich behavioral context beyond a basic 'returns a report'.

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 appropriately sized for the information density; it opens with the core purpose, then uses a semicolon-separated list for output fields and a parenthetical caveat. While slightly long, every sentence contributes valuable detail and there is no fluff.

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 one parameter and no output schema, the description is quite complete: it covers what is returned, the use case, and a notable edge case. It omits explicit mention of page_id semantics and potential failure modes, but the overall context is strong and self-contained.

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 input schema has one required parameter, page_id, with no description attribute (schema_description_coverage = 0%). The tool description never mentions page_id or explains how to find/format the page identifier, leaving the parameter's meaning implicit. Since coverage is low, the description should compensate but does not.

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 uses a specific verb ('Read back') and clearly identifies the resource (what a canvas actually rendered, as JSON). It distinguishes itself from render_preview by explicitly being a companion that returns structured data instead of an image, and enumerates the returned fields.

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 context for when to use it: 'Use it to verify a render — catch clipping, confirm live data, read the real colours — without parsing a PNG.' It references the companion render_preview but does not explicitly name alternative tools or specify when not to use it, missing the 'exclusions' bar for a 5.

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