Forget XMemo memory or TODO

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

The description adds significant behavioral context beyond the annotations: it explains that the default is a recoverable soft delete reversible by restore_memory, while mode='hard' is permanent and unrecoverable, requiring explicit user confirmation. This goes well beyond the destructiveHint annotation by detailing nuances and recovery options.

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 concise and well-structured: it opens with the core action and resource, then details targeting and deletion modes, and closes with a cautionary instruction. Every sentence adds value, and it is appropriately sized for the tool's complexity.

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 the tool's complexity (7 parameters, an output schema, and supportive annotations), the description covers the essential aspects: what is deleted, how to target, the deletion modes, and the prerequisite to resolve ambiguity. It leverages the schema and annotations to avoid redundancy, leaving no major gaps for selection and invocation.

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 the baseline is 3. The description enriches the schema by clarifying that targets can be 'current/latest', an exact memory reference, a TODO ID from list_memory_todos, or a transaction ID from list_ledger_transactions, which is more specific than the schema's target description. However, it does not explain the vague query_hint parameter, leaving a minor gap.

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 tool's action ('Delete one memory, TODO, or Ledger transaction') with specific targeting options, distinguishing it from sibling tools like restore_memory and list_memory_todos. It uses a specific verb with resource and scope, making the purpose immediately clear.

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 provides explicit guidance on when to use the tool (to delete a memory, TODO, or ledger transaction) and how to specify targets (exact memory reference, TODO ID from list_memory_todos, transaction ID from list_ledger_transactions). It also warns to resolve ambiguous targets and restricts hard delete to after explicit user confirmation, effectively saying when not to use it without confirmation.

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