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

Far exceeds the annotations: it details exactly what the archive destroys (removal from bed lists in app and tools, care schedules stop, queued plantings skipped), what survives (weather history keeps the name), irreversibility ('The app has no way to restore it'), and the blocking condition. The destructiveHint annotation only flags danger; the description explains its scope.

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?

Five short sentences, front-loaded with the core action, then consequences, then the blocking rule, then identification. No sentence is redundant, and the irreversibility warning is placed prominently.

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 destructive, non-idempotent mutation with no output schema, the description covers everything an agent needs: side effects, irreversibility, failure precondition, and how to identify the target. 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 description coverage is 100%, so both 'bed' and the optional 'garden' are already documented in the schema. 'Identify by bed name' reinforces the required parameter but adds no format or syntax detail beyond it, so the baseline of 3 is correct.

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 ('remove a bed from the garden') and immediately disambiguates the soft-delete semantics ('Siltwell archives it'), which reconciles the delete_bed name with the 'Archive a bed' title. An agent can distinguish this from update_bed or delete_planting without opening a schema.

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 precondition and remedy: 'Blocked while the bed has active plantings; remove or finish those first.' That tells the agent when the call will fail and what to do instead. It stops short of naming the sibling tools (delete_planting, delete_planned_planting) that satisfy that precondition, so it is clear context rather than full routing.

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