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

With no annotations, the description carries the full burden and does well: it discloses deterministic behavior, no AI, no rate limit, honest flagging of unresolvable fills, and the mode-specific outputs. It does not cover error behavior, input prerequisites, or whether harden rewrites the source in place versus returning a new source.

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 front-loaded with the core purpose and uses a numbered list to organize the four capabilities. It is dense but justified by the multi-mode tool, with only minor verbosity in the parenthetical explanations.

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 an 11-parameter tool with no annotations and no output schema, the description is fairly complete: it explains each mode's purpose, key behavior, and the type of result returned. It could be stronger by clarifying output shape, error cases, and whether any mode writes or mutates external state.

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 parameter documentation is already strong. The description adds useful meaning beyond the schema by explaining the distinctions among scan, harden, contrast, print, and layout, including why source hardening cannot be achieved by scanning rendered output.

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 states a specific purpose, 'Diagram quality QA,' and enumerates four concrete capabilities: contrast checking, mermaid source hardening, print-safety checks, and arrow-crossing reduction. It is clear what the tool does, though it does not explicitly differentiate itself from diagram-adjacent siblings such as convert_diagram or describe_diagram.

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?

Each mode is given a clear usage scenario, and the description explains why source hardening is distinct from rendered scanning. It stops short of naming when not to use the tool or pointing to specific alternative sibling tools.

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