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

Beyond the annotations, the description discloses critical behavior: schema-invalid items reject the entire call and save nothing, while valid items the server cannot store are reported individually. It also adds consent and secret-handling requirements, which are substantial operational details not covered by the annotations.

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 front-loaded with the core action and then adds the consent rule, atomic validation behavior, partial storage reporting, and secret-handling warning. Every sentence carries useful information and there is no redundant wording.

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 important behavioral and safety context for a complex import tool with no output schema and 0% schema description coverage. However, it leaves major schema details unexplained, including most item kinds, required fields, batch limits, and the meaning of batch_id.

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 description mentions past chat turns and a document with kind "document," but the schema also supports memory_write, memory_forget, consent, and capture_session items. With 0% schema description coverage, the description does not explain required item fields, the items array limit, batch_id, or the nested payload and speaker structures.

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 names a specific verb and resource: saving past chat turns in order, or one document of kind "document." This is more informative than a tautological title, but it does not differentiate the tool from siblings such as memory_capture_turn or memory_remember.

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 gives a clear consent prerequisite: "Only import with the user's OK." It also implies the import use case for historical chat turns or a document, but it does not state when to use this instead of sibling tools like memory_capture_turn or memory_remember.

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