memory_ingest

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

Annotations mark this as a non-read-only, non-idempotent write but say nothing about timing. The description discloses the crucial asynchronous behavior (nightly 'dream' pipeline distills messages later) and the return shape, which is well beyond what the annotations convey.

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 tight sentences: purpose first, deferred-processing caveat second, alternative and return value last. Every sentence earns its place with 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?

Though there is no output schema, the description supplies the return shape ({ conversation_id, message_ids }) and how to use message_ids downstream. The deferred-processing model is explained, so an agent has everything needed to call and reason about the result.

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 100%, so parameters (source, messages, namespace, auto_extract, conversation_id) are fully documented by the schema. The description adds no per-parameter meaning, so the baseline 3 applies; the schema does the heavy lifting.

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 and resource: 'Store raw chat messages as conversation history.' It also clarifies the deferred nature of the operation and explicitly names memory_upsert as the immediate-save alternative, letting an agent distinguish it from siblings like memory_upsert or memory_search without opening schemas.

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?

Explicitly routes the agent: 'To save a fact right away, use memory_upsert,' which gives both the when-to-use and the alternative. It also points to memory_pin as the downstream consumer of message_ids, so the usage flow is fully specified.

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