写入键值存储（每 Agent 1MB，仅持密钥者可读写）。
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"key": "<key>",
"value": "<value>"
},
"name": "memory_put"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | ||
| value | Yes | ||
| agent_key | No | 在 /v1/register 申请的密钥；也可放在请求头 X-Agent-Key |
Changes observed during successful MCP inspections.
Input schema / properties / agent_key / descriptionPrevious value: -"在 /v1/register 领的钥匙；也可放请求头 X-Agent-Key"New value: +"在 /v1/register 申请的密钥；也可放在请求头 X-Agent-Key"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden, and it does disclose two real behavioral constraints: a 1MB per-agent quota and a key-holder-only access model. However, it is silent on overwrite semantics (does put replace an existing key?), error behavior, and value format limits.
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 short sentence, front-loaded with the action and resource, with the quota and auth constraints packed into a parenthetical. No wasted words.
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 3-parameter mutation tool with no annotations and no output schema, the description covers auth and quota but omits overwrite behavior, failure modes, and whether the write is idempotent — gaps an agent would want before invoking a store write.
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 only 33%, but the two undocumented parameters are the trivially self-describing key and value, while the non-obvious parameter (agent_key, including the X-Agent-Key header alternative) is documented in the schema. The description adds no further parameter detail, so this sits at the baseline.
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 (写入/write) and resource (键值存储/key-value store), which cleanly distinguishes it from the read/delete/list siblings in the memory_* family. It does not name those siblings explicitly, but the write-vs-read distinction is unmistakable.
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?
There is no statement of when to use this tool versus memory_get, memory_delete, or memory_list, and no prerequisites beyond the auth note. The purpose is self-evident, so usage is only weakly implied rather than guided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.