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

Goes beyond annotations by explaining the queuing behavior ('only queues the change for the human's review') and the visibility consequences of a move (team vs personal exposure). Annotations already cover idempotency and non-destructiveness, so the description adds useful context without contradiction.

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?

Three sentences front-load the core purpose, then behavior, then parameter source. Each sentence earns its place; no filler.

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 purpose, usage context, behavioral consequences, and parameter source. It doesn't describe the return value, but there is no output schema, and the human-review outcome is explicitly stated. Some missing details like failure conditions are minor.

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 covers all four parameters at 100% with clear descriptions. The description adds the source for memory ('Use the #handle from the read') but that is already present in the schema. No additional meaning beyond the schema.

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 ('PROPOSE'), resource ('a memory belongs in a different project'), and distinguishes itself from actually moving by saying 'you never move it yourself' and 'only queues the change for the human's review.'

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 clear context for when to use it (when you believe a memory belongs elsewhere) and instructs to use the #handle from the read. It stops short of naming alternative sibling tools, but 'you never move it yourself' establishes that this is the proposal path, not the execution path.

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