memory_write_cancel

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

No annotations are provided, so the description carries the full burden. It goes beyond the basic action by disclosing TTL expiration, the behavior when the ID never existed, and the returned `existed=False` field. This is transparent for a cancellation operation.

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?

Two sentences, zero waste. The main action is stated first, then the parameter source, then the expiration behavior. Ideal size for the information provided.

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?

The tool is simple (one parameter, no nested objects) and the description fully explains what to pass and what to expect in edge cases. An output schema exists, so return values are already structured, and the description adds the necessary nuance.

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%, so the description must compensate. It explains that `pending_id` comes from the original write response, which is crucial context not in the schema. For a single parameter, this is sufficient guidance.

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 uses a specific verb ('Drop') and resource ('a pending memory_write') and clearly states the action is cancellation without committing. It distinguishes from sibling tools like memory_write_confirm (which commits) and memory_write (which creates the pending write).

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 explains when to use the tool ('Pass the pending_id from the original write response') and provides essential context (1-hour expiration). It doesn't explicitly name alternatives or exclusions, but the sibling tool names imply these, and the context is clear enough for an agent to select this tool for cancelling pending writes.

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