memory_add

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

With no annotations, the description carries the transparency burden. It communicates that the memory is 'durable' and stored in 'shared Notion memory,' which conveys persistence and storage location. It also adds content policy guidance ('Do NOT store secrets, tokens, or throwaway information') and even specifies bugfix records should include root cause + fix. It does not describe the write response or failure behavior, but the core mutation behavior is disclosed.

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 carry all necessary information: the first states the action and target, the second lists concrete triggers and exclusions. Everything included is purposeful and front-loaded, with no filler or redundancy.

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 create-only tool with six parameters and no annotations or output schema, the description gives strong when-to-use context, content policy, and storage destination. It does not explicitly direct agents to memory_update for editing existing memories or describe the call's return behavior, but the core information needed to invoke this tool correctly is present.

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 67%, so the description is partly responsible for parameter meaning. It adds useful content-level semantics, such as storing root cause + fix for bugfixes and avoiding secrets, which informs the content parameter. However, it does not clarify the category or importance enums, and those parameters have no schema descriptions. This is partial compensation, not complete.

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 begins with a specific verb and resource: 'Save a new durable memory into the shared Notion memory.' The word 'new' clearly marks this as a create operation, distinguishing it from siblings like memory_update and memory_delete, and 'durable' and 'shared' add scope. This is unambiguous and well differentiated.

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 lists when to use the tool: user preferences, project decisions, conventions, non-obvious bug fixes, and learned context. It also provides a clear exclusion: do not store secrets, tokens, or throwaway information. This gives an agent decisive routing criteria without needing to infer.

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