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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely new behavioral context: an x402 payment requirement and the exact cost ($0.006 USDC per call) plus the shape of the returned coordinates. It stops short of 5 by omitting rate limits or failure behavior.

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?

A single dense sentence plus a short pricing sentence, front-loaded with the core action and output modes. Every clause contributes, though the parenthetical mode enumeration is slightly crammed rather than cleanly structured.

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?

With no output schema, the description partially compensates by describing coordinate output formats, and it covers the dominant mode parameter. However, for a 5-parameter tool with 40% schema coverage it leaves the image-input channel and max_objects behavior unexplained, so it is only adequate rather than complete.

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 description coverage is only 40%, so the description must carry more weight than it does. It usefully clarifies mode=detect/point (matching the schema) and gives target examples, but says nothing about image_url vs image_base64 inputs or what max_objects controls.

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?

States a specific verb and resource ('Find things in an image by description') plus the exact output forms (bounding boxes via mode=detect, centre points via mode=point) and coordinate spaces. This level of output specificity clearly separates it from siblings like vision_ask and image_describe without needing to name them.

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?

Gives clear usage context ('open-vocabulary detection ... for any phrase') with two concrete example phrases, so an agent knows what inputs are appropriate. It never names an alternative tool or states when not to use it versus vision_ask/image_describe, keeping it short of a 5.

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