delete_meal

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

Annotations already declare destructiveHint=true, so the destructive nature is established. The description adds value by specifying it's a 'soft-delete' (as opposed to hard delete) and that it checks expected revision before proceeding. However, it doesn't explain what happens on revision mismatch (error? no-op?), how to obtain the expected revision, or whether restore_meal can undo it.

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?

One concise sentence that packs in soft-delete semantics and the revision-check precondition. No wasted words; appropriately brief for a simple two-parameter deletion operation.

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 annotations declaring destructive behavior and an output schema present, the tool is reasonably specified. The description covers the key behavioral nuance (soft-delete, revision check). However, given there are sibling tools like restore_meal and list_meals that could provide context, and a 0% schema description coverage, additional detail about revision mismatch behavior or undo-ability would strengthen completeness.

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 0% and there are no parameter-level descriptions in the schema, so the description carries the burden. It mentions 'expected revision' conceptually, which hints at the meaning of the expected_revision parameter, and meal_id is self-evident. But it doesn't explain where to get the expected_revision value (from get_meal or get_meal_history?), nor its exact semantics.

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 verb ('Soft-delete') and resource ('a meal'), and distinguishes from siblings like 'restore_meal' and 'update_meal' by indicating this is a deletion operation. It's clear but brief; the soft-delete nuance adds specificity beyond what the name alone conveys.

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 implies when to use it (when deleting a meal) and the revision-check mechanism suggests an optimistic-concurrency pattern, but it doesn't explicitly state when NOT to use it or contrast with alternatives like 'restore_meal' or 'update_meal'. The revision requirement hints at context but isn't elaborated.

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