Submit a candidate company memory with immutable evidence for review before it becomes authoritative.
Create immutable evidence and a non-authoritative candidate memory.
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | ||
| rationale | No | ||
| statement | Yes | ||
| tenant_id | No | local | |
| project_id | No | ||
| memory_type | Yes | ||
| classification | No | restricted | |
| source_locator | No | mcp://proposal | |
| evidence_content | Yes | ||
| source_native_id | No |
Changes observed during successful MCP inspections.
v2.1.3Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses two meaningful behavioral traits: evidence is immutable and the resulting memory is non-authoritative/candidate. However, with no annotations, it omits side effects, permissions, whether the proposal enters a review workflow, and what the response contains.
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 concise sentence and front-loads the core purpose. But it is so sparse that it sacrifices the structure and detail needed to support correct invocation of a 10-parameter tool.
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 tool with 10 parameters, no output schema, and no annotations, a one-sentence description is severely incomplete. The agent lacks guidance on how to construct a valid proposal, what counts as evidence, and what happens after the memory is proposed.
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% and the description adds no parameter-level meaning. Ten parameters, including required fields like memory_type and evidence_content, are left completely unexplained, forcing the agent to guess allowed values and relationships.
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 names a specific action ('Create') and a clear resource ('immutable evidence and a non-authoritative candidate memory'). It hints at differentiation from authoritative/trusted memory tools, though it does not explicitly name a sibling or explain the proposal lifecycle.
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 'non-authoritative candidate' phrasing implies this is for proposing memory rather than finalizing trusted memory, but there is no explicit when-to-use/when-not-to-use guidance. An agent must infer the distinction from sibling tool names like trusted_memory_propose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.