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

Beyond annotations, the description adds valuable behavioral context: it flags the sensitive-tier approval flow, explains how approvals behave (from-now-on vs just-once), and instructs the agent to call on first clear ask without re-asking. It also mentions quality characteristics ('Preserves details and creates clean vector paths'). It doesn't explain the destructiveHint=true annotation, but it doesn't contradict it either.

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 organized into three purposeful paragraphs: core action, routing triggers, and approval/credit guidance. Each sentence contributes to helping the agent decide and call correctly. It's slightly longer than the minimal necessary, but every section serves a clear function and the main action is front-loaded.

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?

The description covers input types, routing, cost, and approval behavior well, but there is no output schema and the description never states what the tool returns (e.g., an SVG file or artifact ID). Also, the destructiveHint annotation is not explained. These are meaningful gaps for agents that need to use the result or understand side effects.

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?

All 7 parameters have complete descriptions in the schema (100% coverage), so the baseline is 3. The description doesn't add further parameter-level guidance beyond what the schema already provides, which is acceptable since the schema fully documents fields like image_url, artifact_id, and isolate_subject.

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 first sentence states the exact operation: 'Convert an existing raster image (PNG, JPG, WebP) to SVG vector format using Recraft.' This is a specific verb (convert) + resource (raster image) + target format (SVG). The word 'existing' distinguishes it from generation tools that create images from scratch, so it differentiates from the sibling generate_vector_image without needing to name it.

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?

A dedicated Routing section lists trigger phrases ('vectorize this', 'convert to SVG', 'make scalable') and explicitly notes the 1-credit cost. This gives clear context on when to invoke. However, it doesn't name alternatives or state when not to use it (e.g., for text-to-vector generation or background removal), so it stops short of the full 'when/when-not/alternatives' ideal.

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