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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds substantial extra behaviour: the mutual-exclusivity cap ('at most one of frameId, region or nodeIds'), effectiveScale and low_detail warning thresholds, clipping of edges in a partial render, watermark plan override ('always when the organization's plan requires it'), and that the PNG is a still of animated edges. It also enumerates known rendering limits (external/AVIF placeholders, one-colour emoji, nested SVG text), which is exactly the kind of caveat structured fields cannot convey.

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?

Purpose and scale are front-loaded and every clause carries information, but the body is a single dense paragraph with heavy parenthetical nesting and some restatement of enum/scale facts already in the schema. Slightly more structural breaks (scope rules, returns, limits) would improve scanability without losing content.

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?

With no output schema and nine parameters, the description carries the return contract itself: it lists the full result object, explains the meaning of effectiveScale, and decodes each warning code (low_detail, watermark_style_adjusted, external_images_placeholder, empty_diagram). Combined with the documented rendering limits, an agent has everything needed to call this and interpret the result.

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 the baseline is 3, but the description adds semantics the schema lacks: frameId accepts any node not just a frame, region follows get_canvas coordinates with frames cut to its bounds, and watermark is ignored when the plan forces it (watermarkSource "plan"). The important constraint that only one of the three scope parameters may be used is stated in prose and absent from 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?

Opens with a specific verb and resource ('Renders the diagram ... as a PNG image') plus scope ('or one part of it') and purpose ('for checking a drawing'). It is clearly distinguished from the closest sibling, export_diagram, which is described as making files 'for the person'.

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?

States the agent-side use case ('for checking a drawing') and explicitly routes human-facing file output to export_diagram, which is a real alternative. It does not, however, address when to prefer show_diagram, get_canvas or viewer_poll, so the alternative-routing is partial rather than exhaustive.

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