Remember, update, supersede, or archive canonical agent memory using action, key, provenance, and idempotency key to keep shared context accurate.
MANAGER WRITE: remember, update, supersede, or archive canonical memory.
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | ||
| tags | No | ||
| scope | No | project | |
| value | No | ||
| action | Yes | ||
| provenance | Yes | ||
| idempotency_key | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. 'MANAGER WRITE' implies mutation, but nothing is said about required permissions, reversibility, why idempotency_key and provenance are mandatory, or what supersede/archive do to existing entries. Large gaps for a mutation tool with zero annotation coverage.
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?
A single front-loaded sentence with no wasted words and the operation set stated up front. It is concise, though the 'MANAGER WRITE:' prefix is a mild stylistic artifact rather than content.
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?
An output schema exists so return values need no explanation, but a 7-param mutation tool with no annotations and 0% schema coverage requires far more than this one-liner: no scope defaults, no idempotency semantics, no destructive-action warnings, and no action-selection guidance.
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 both schema and description leave all 7 parameters undocumented. The description echoes the action enum values but adds nothing about key, value, tags, scope, provenance, or idempotency_key semantics, failing to compensate for the coverage gap.
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+resource ('WRITE... canonical memory') and enumerates the four operations, which distinguishes it from read siblings like ai_memory_search and ai_memory_get. It's clear what the tool does, though it never explicitly names the read-side counterparts.
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?
Lists the four actions but gives no guidance on when to choose remember vs update vs supersede vs archive, no prerequisites, and no exclusions. An agent must infer the routing logic entirely from the enum.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.