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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description goes well beyond that by disclosing the validation behavior (layout checks for box overlaps and edge crossings, process checks for unknown ids with line numbers, single-branch decisions, unreachable and dead-end steps) and the hard limits of 150 nodes and 300 edges, which an agent needs before constructing input.

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?

Front-loaded with the trigger condition, then inputs, then outputs, then limits, then exclusions — a logical order with no filler sentences. It is a dense single paragraph, and the long enumeration of return artifacts and checks makes it heavier than strictly necessary, but each clause carries information an agent would otherwise have to discover by trial.

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 7-parameter generative tool with an output schema, the description covers trigger, input modes, output artifacts, validation feedback, and hard limits. Even though the output schema exists and return values need not be explained, the description's summary of what comes back (widget, checks, Mermaid, SVG/PDF downloads) helps the agent set user expectations correctly.

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 real meaning the schema does not: it explains the two mutually exclusive input modes (text with one edge per line vs. nodes plus edges) and states "Leave empty when you give nodes and edges," which resolves an ambiguity the schema leaves open. It also names the accepted node shapes and label syntaxes in prose, though it does not elaborate on page_size or edge_style beyond the enum descriptions.

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?

States a specific verb and resource (generate a flowchart) and enumerates the concrete artifacts it produces (Mermaid text, SVG, PDF, interactive widget). It also draws a hard boundary against adjacent diagram types (swimlanes, org charts, mind maps, sequence diagrams, data charts), so an agent can tell exactly what this tool is and is not.

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?

Opens with an explicit trigger condition ("Use this when the user wants a flowchart, process diagram, decision tree or workflow chart...") and closes with explicit when-not conditions (no swimlanes, org charts, mind maps, sequence diagrams, data charts; no saving or sharing). With no sibling tools, the exclusions do the routing work that sibling differentiation would otherwise do.

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