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

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description adds significant behavioral context: it explicitly states the tool never raises protocol errors on invalid input, instead returning a structured error object with guidance. It also confirms read-only and idempotent behavior, which reinforces safety for retries. There's no contradiction with annotations; in fact, the description amplifies the annotation hints with concrete error-handling details.

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 well-structured and front-loaded: it opens with the core purpose, gives a concrete example with a typical input/output, provides direct usage guidance, and closes with error-handling details. Every sentence adds value; there is no fluff or repetition. It is substantial but each part is necessary for correct tool invocation.

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?

Given the tool's moderate complexity (5 params, multiple presets, modes) and the presence of a rich output schema and annotations, the description covers everything needed: purpose, example, usage, error behavior, and safety. The error-handling details are particularly valuable for an agent to interpret unexpected responses. The description is complete enough that the agent can use the tool correctly without additional probing.

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?

The input schema already has 100% coverage with rich descriptions for all parameters, including acceptable values and defaults. The description adds value by showing the expected output shape and the box-transform formula, which clarifies how parameters flow into results. However, it doesn't elaborate on each parameter beyond the schema, but since the schema is already thorough, this is sufficient. A 4 is appropriate because the description's example adds meaning beyond the schema without over-explaining.

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 clearly states the tool computes scale, padding, and crop for model input sizing, with a concrete example. It explicitly distinguishes itself from image_probe, and its purpose is unambiguous relative to sibling tools like bbox_convert or nms.

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?

The description gives explicit usage guidance: 'Use before feeding an image to a fixed-input model' and even names the alternative for a different need ('Not for finding out the image's size in the first place - that is image_probe'). This tells the agent exactly when to invoke it and when not to, satisfying the when/when-not criteria.

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