Preview a scientific figure template

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

The description discloses both the primary behavior (returning image content) and an important side effect (optionally copying to a project-local directory). This adds context beyond the annotations, which only indicate idempotent and non-destructive behavior. It does not cover failure modes or permission needs, but for a simple preview tool this is acceptable.

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 two sentences, front-loaded with the primary action, and every sentence earns its place: the first gives the core behavior, the second explains the optional copy and intended use case.

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 tool with two parameters, an output schema, and behavioral annotations, the description covers purpose, usage context, and side effects. The return format is handled by the output schema, so no further detail is needed.

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?

With 50% schema coverage, the description helps fill gaps. It clarifies that templateId is the 'selected candidate' and that destination enables a local copy for view_image. The schema alone leaves templateId's role ambiguous, so the description adds meaningful semantic context.

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 opens with a specific action: 'Return the selected candidate preview as standard MCP image content.' It names the resource (candidate preview) and distinguishes the tool from siblings by focusing on visual auditing before final recommendation.

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?

It clearly states when to use: 'Use this to visually audit the top retrieval candidate before making a final recommendation.' It also mentions a follow-up path (copying for Wisp Agent to call view_image), but it does not explicitly contrast with sibling tools like figure_library_open or figure_library_materialize.

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