image_annotate

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

Discloses key behaviors: creates a new file, refuses out_path collisions with input. Beyond annotations (idempotentHint=true, destructiveHint=false), adds context about file safety and collision prevention.

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?

Two well-structured sentences: first describes primary action and constraints, second details output behavior. No filler, information 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?

Thoroughly covers the tool's functionality given 3 required params and no output schema. Explains input format, output creation, and safety constraint. No obvious gaps.

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 0% schema description coverage, the description fully compensates: explains the mark format as {x, y, w, h, label?}, limits to 50 marks, and clarifies out_path collision behavior. Adds meaning far beyond the schema.

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?

Explicitly states the verb 'draw labelled rectangles' on 'a copy of an image', with specific mark structure. Clearly distinguishes from sibling tools like image_crop and image_convert by focusing on annotation.

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?

Provides concrete usage scenario: 'point at regions of a drawing or screenshot when words alone are ambiguous.' Implies when to use, though does not explicitly state when not to use or list alternatives.

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