Merge units

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

Annotations already flag destructiveHint=true and readOnlyHint=false; the description adds concrete behavioral details beyond that: the source unit is deleted, ingredient references are rerouted to the target unit, and a two-step confirmation token is required. It does not discuss reversibility or the blast radius of changes, but with annotation coverage this is valuable and non-contradictory context.

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 exactly two sentences: the first establishes the core purpose and destructive effect, the second covers the critical confirmation protocol. There is no filler or redundant detail; the structure is efficient and front-loaded.

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 that an output schema exists and annotations convey the safety profile, the description provides the essential operational behavior: merge action, source deletion, and the token round-trip. It is sufficient for an agent to select and start invoking the tool correctly, though it does not mention edge cases like merging a unit into itself or idempotence behavior.

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%, and each property is already described in the schema: from_id is 'the unit to merge away — this one is deleted', to_id receives references, and confirm_token is 'from a previous call... Omit on the first call'. The description's token explanation is essentially a restatement of what the schema already carries, so it adds little extra meaning.

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 states a specific action and resource: it 'points every ingredient that uses one unit at another one and deletes the source unit', which clearly conveys the merge-and-delete semantics. This distinguishes it from sibling tools like merge_foods, where the target is foods rather than units.

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 explicitly explains the confirmation flow: 'call once to receive a token, then again with that token', giving the agent a precise invocation pattern. It does not, however, describe exclusions or explicitly contrast with alternatives such as merge_foods, so it stops short of full when/not-to-use guidance.

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