Searches agent memory for stored credentials and API keys
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "agent_memory_search"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| query | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full disclosure burden and reveals almost nothing. For a tool that touches credentials and API keys it does not say whether secrets are returned in plaintext or redacted, whether the call is audited, whether it requires authorization, or how results are paged or limited.
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 zero wasted words, which is good, but the terseness here is under-specification rather than efficiency. The one sentence could have absorbed essential scoping detail at no structural cost.
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 security-sensitive search tool with no annotations, no output schema, and undocumented parameters, this definition is far too thin. An agent cannot determine result shape, sensitivity handling, or how this differs from the vault and token siblings before invoking it.
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% for the single 'query' parameter, and the description adds no semantics about what it matches against (key name, service, secret value) or what happens if it is omitted. With the schema providing no meaning and the description providing none either, the parameter is effectively undefined.
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 verb (searches) and a resource (agent memory) plus the target content (stored credentials and API keys), so the general purpose is inferable. However, it does not distinguish itself from siblings like vault_lookup, token_vault, or credential_broker, and 'agent memory' is left undefined, so an agent cannot tell whether this is a general memory search or a secrets-specific lookup.
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?
No when-to-use, when-not-to-use, or alternative-selection guidance is provided. With five closely related siblings (credential_broker, vault_lookup, token_vault, oauth_refresh), the absence of any routing guidance leaves the agent to guess.
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.