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

Annotations already declare this is a non-destructive, non-idempotent mutation. The description adds useful behavioral scope by saying it 'Adds an item and changes nothing else', clarifying that it is an additive create rather than an update with side effects. It still does not explain duplicate/retry behavior for the non-idempotent write path.

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 short sentences, front-loaded with the action and scope, and no wasted text. The second sentence immediately clarifies side-effect behavior.

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 six-parameter create tool, the description covers the core action, path scope, and additive side-effect profile, while annotations and schema handle safety and most parameter details. The main remaining gap is that it does not explain what is returned or how the operation_id/idempotency_key parameters relate to retry behavior, but the schema fills part of that gap.

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 coverage is 67%, and the description meaningfully compensates for the undocumented path parameter by specifying it is 'workspace-relative'. The remaining parameters, including operation_id and workspace_id, are already described in the schema, so the description adds enough semantic value without repeating them.

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-resource pair: 'Save a new memory', scoped to 'a workspace-relative path' and the connected Pathrule workspace. The word 'new' and the phrase 'Adds an item' distinguish it from update/read/delete siblings without needing to name them.

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?

It clearly signals the intended case: creating a new memory rather than changing an existing one. It does not explicitly name update_memory as the alternative for existing items, but the 'new' condition gives enough context for correct selection.

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