apply_memory_patch

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

Annotations already indicate destructive and non-idempotent behavior. The description adds context by requiring a previously previewed patch and a one-time confirmation ID, which explains the non-idempotence and workflow. This goes beyond simply repeating annotation hints.

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?

A single, front-loaded sentence that contains all essential information without filler. It is appropriately concise for the tool's narrow purpose.

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 description covers the key workflow constraint (previewed patch) and the one-time ID, which is sufficient given the sibling tools and simple parameter set. However, it does not describe success/error behavior or clarify editSessionId, which would improve 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?

The schema provides zero descriptions for both parameters. The description explains 'confirmationId' as a one-time confirmation ID but gives no information about 'editSessionId', its origin, or its relation to the session. With 0% schema coverage, the description only partially compensates.

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 action ('apply') and the resource ('previously previewed patch'), and specifies the one-time confirmation ID. This distinguishes it from sibling tools like preview_memory_patch and undo_last_patch.

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 limits usage to 'only a previously previewed patch' and emphasizes the one-time nature of the confirmation ID, implying a prerequisite of prior preview. However, it does not explicitly state when not to use the tool or mention alternatives.

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