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

Annotations already declare readOnly/idempotent/non-destructive, and the description reinforces this with 'Saves nothing' rather than contradicting it. It adds genuinely useful behavior beyond annotations: duplicate detection within the drop and against the library, and the deferred-error/retry contract.

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?

Three dense sentences, front-loaded with the action and categories, with no filler. The critical non-destructive and retry facts are stated compactly.

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 does the work of describing returns (category assignment, unsure-with-two-candidates, duplicate reports) and the deferred error case. It is largely complete, though the result shape/index mapping is left to the schema.

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 100%, covering sha256, image_url, file_name, and board_id in detail, so the schema carries parameter meaning. The description adds only a light hint about drop order/results indexing, which the schema already states.

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 precise verb ('sort') and resource ('photos dropped on the Shoot Board'), then enumerates the output categories (garment, avatar, location, reference, unsure-with-two-candidates) and the duplicate reporting. The 'Saves nothing' clause immediately separates it from write siblings like mcp_commit_intake.

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?

Clarifies it is a non-committing pass, implies the commit step lives in a sibling, and gives clear retry guidance for the deferred case. It stops short of naming the alternative tool or stating explicit when-not conditions.

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