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

Annotations already mark the tool read-only, non-destructive and idempotent; the description goes well beyond that by disclosing layout differences for diagram kinds, parse-error details (line/column), the Open in Line9 link, panel vs terminal rendering, sign-in/branding behavior, and the impossibility of publishing/saving. None of this contradicts 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?

Dense but efficient: the core purpose and trigger come first, followed by output, failure handling, client differences, and constraints, with no filler or repeated schema text. The length is justified by the number of behavioral nuances an agent must know before invoking this tool.

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 complexity — custom layout, frontmatter options, panel vs terminal output, parse-error recovery, auth/branding, and publish limitations — the description is complete. It even covers the failure retry loop ('fix the named line and call again'), and the return-value burden is covered by the output schema plus the explicit verdict summary.

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; the description adds real value by explaining that `plan` is an opaque hint from a prior result and by prohibiting style/theme arguments ('set ... in the source itself, never as arguments'). It also clarifies what frontmatter in `source` controls, which goes beyond the schema's property names.

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 — 'Render Mermaid source with Line9's layout engine' — and immediately distinguishes rendering from the get/list siblings. It also specifies what the call produces (verdict, link, panel rendering), so an agent can tell exactly what the tool does.

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?

Explicit trigger condition: 'Call this whenever you write or change Mermaid and the user should see the result.' It also states clear exclusions ('cannot publish or save', 'not with the Line9 CLI') and gives branch instructions for panel vs no-panel clients, so both tool choice and follow-up action are unambiguous.

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