Store a text record into a named partition, tagging it, enforcing a size cap with oldest-entry eviction, and erasing it on expiry or session close.
Remember into a partition: the record is tagged partition:, counted against its cap (the oldest is evicted with a tombstone when the cap is reached), and erased by its expiry or at close.
| Name | Required | Description | Default |
|---|---|---|---|
| key | No | ||
| tags | No | ||
| text | Yes | ||
| partition | Yes |
Changes observed during successful MCP inspections.
v2.39.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and does so admirably: it discloses tagging format, cap enforcement, eviction behavior (oldest gets a tombstone), and erasure triggers (expiry or close). This is rich behavioral detail that goes far beyond a generic 'store a record' statement.
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 a single front-loaded sentence that moves from the core action ('Remember into a partition') to the specific consequences. Every clause adds behavioral information with no filler or repetition.
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 partition behavior well but omits parameter semantics for 'text', 'key', and 'tags', and does not state whether the partition must already exist or how the cap is configured. Given no output schema and no annotations, an agent still has several gaps to fill before invoking the tool correctly.
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 0%, so the description must compensate, but it only clarifies 'partition' by explaining the tag format. It does not explain the meaning or expected content of 'text', 'key', or 'tags', leaving agent uncertain about required and optional parameter usage.
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 ('remember') and resource ('partition') and details the exact behavior: tagging with partition:<name>, cap counting, eviction with tombstone, and erasure by expiry or close. This clearly distinguishes it from plain 'remember' and 'remember_decision' siblings by emphasizing partition semantics.
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 implies partition-based memory use with eviction and expiry, which suggests when an agent might want this tool. However, it does not explicitly state when to use this over 'remember', 'open_partition', or 'close_partition', nor does it provide any exclusion criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.