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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: it documents the tie-breaking rule and determinism guarantee, the premium license requirement, and a precise error contract (never raises a protocol error; returns {"error": ...}) plus the safe-retry implication. These are exactly the behavioral traits annotations cannot express.

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?

Front-loaded with purpose and algorithm, then example, then usage and error handling — a sensible order with little filler. The sample return value partly duplicates the output schema, which is the only reason it falls short of a 5.

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 6-parameter algorithmic tool with a full output schema, the description covers purpose, algorithm, determinism, licensing, error behavior, and sibling routing. Return values are explained by the output schema, so the example is a bonus rather than a gap-filler; nothing an agent needs to call this correctly is missing.

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 coverage is 100%, so the baseline is 3; the description earns more by supplying a concrete worked input and by surfacing a cross-parameter constraint the schema cannot state ("boxes and scores must be the same length"). It does not mention box_format, image_width/height, or the meaning of iou_threshold beyond "the threshold", leaving those entirely to 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?

Opens with a specific verb and resource ("Remove duplicate detections of the same object") and immediately names the algorithm (greedy non-maximum suppression) so an agent knows exactly what operation this is. It also distinguishes itself from the siblings bbox_convert and detection_metrics by name, so no schema inspection is needed to tell them apart.

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?

"Use after a detector that emits overlapping boxes" gives a positive trigger, and "Not for scoring against ground truth (detection_metrics) and not for format changes (bbox_convert)" gives explicit exclusions mapped to the correct alternatives. This is a full when/when-not/alternative routing statement.

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