save_memory

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

With no annotations, the description fully discloses the tool's side effects: temporal decay ('will have temporal decay applied'), automatic forgetting ('forgotten if not used regularly'), and potential promotion to long-term storage. It also documents error behavior with 'Raises: ValueError.' These are significant behavioral traits that go beyond a simple save 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?

The description is structured efficiently: a one-sentence purpose, two sentences on behavior, a compact Args list, and a Raises clause. It avoids repetition and keeps the total length appropriate for a tool with six parameters, all of which are covered.

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 creation tool with no annotations, the description provides a complete picture: purpose, behavior, parameter details, and validation errors. Since an output schema exists, the lack of return-value documentation is acceptable. The only missing element is explicit alternative guidance, but that's captured under usage guidelines.

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 input schema only specifies types and names, providing no descriptions for any parameters. The description compensates by explaining each parameter's semantic role (e.g., 'tags: Tags for categorization') and adding explicit constraints like 'max 50,000 chars' and 'max 50 tags, each max 100 chars.' This gives the agent concrete invocation requirements.

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 opens with 'Save a new memory to short-term storage,' using a specific verb ('save') and resource ('memory') with a clear target. It distinguishes from sibling tools like promote_memory and touch_memory by emphasizing creation and short-term placement. This unambiguous phrasing makes the purpose immediately obvious to an agent.

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 phrase 'short-term storage' sets clear context for when this tool is appropriate—creating a new memory intended for short-term use. However, it does not explicitly name alternatives or state when to avoid using this tool in favor of a sibling. It is more than implied guidance but lacks explicit exclusionary language.

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