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

Far exceeds what the annotations convey: annotations only flag destructive=true and idempotent=false, while the description explains exactly what moves (bags, shots, recipes, recommendations), the conditional behaviors (origins only if target has none, newer lock wins and older is deleted), that the source is archived not deleted, and that the operation is irreversible.

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?

Leads with the trigger, then the consequences, then the safety warning — all within four sentences with no filler. The dense lock-conflict clause is the only heavy sentence, but it is information the agent cannot get elsewhere.

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?

A destructive mutation with an output schema needs the description to cover data migration, edge cases and irreversibility; it does all three. Return values are covered by the output schema, so nothing material 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% and the schema already labels from_bean_id as the duplicate to be archived and into_bean_id as the survivor, so the description is not the sole source. It still adds directional reinforcement and points the agent at list_beans to resolve the numbers before calling.

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 ('fold one coffee into another') plus the exact condition that motivates it ('when the same coffee was registered twice'). This clearly distinguishes merge_beans from update_bean and the register_* siblings.

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 an explicit trigger condition (duplicate registration) and a required pre-flight step: confirm both numbers with the user and look them up via list_beans. It does not name the non-duplicate alternative (update_bean) for cases where the coffees are genuinely distinct, so the when-not case is only implied.

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