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

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds contextual details beyond annotations: it uses 'self-hosted Kroki' and returns a hosted URL for embedding, which informs the agent about the tool's backend and response format.

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 three sentences, front-loaded with the purpose, and includes a concrete example. Every sentence provides useful information without redundancy or 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?

Given the presence of an output schema and comprehensive parameter descriptions, the description is sufficiently complete. It covers purpose, supported formats, return behavior (URL), and even an example request. No critical aspects are missing for the agent to invoke the tool.

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 schema covers all three parameters, so the baseline is 3. The description adds value by showing an example GET URL with 'source' and 'format' parameters, and by elaborating on the 'type' parameter's many options ('and 20+ more'). This helps the agent understand the parameter syntax and flexibility.

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 tool's function: 'Turn diagram-as-code into an image' and lists supported languages (Mermaid, PlantUML, Graphviz/DOT, etc.). It distinguishes itself from sibling tools by describing a unique rendering capability and its output as a hosted URL.

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 on usage—when you have diagram-as-code and want an image. It does not explicitly name alternatives or exclusions, but given the tool's unique scope among siblings, the implied usage is adequate.

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