Submit sourced knowledge items for human review in Filigree, capturing decisions, observations, or corrections without approving, replacing, or publishing memory.
Propose a sourced knowledge item for human review. Cannot approve, replace or publish memory.
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes | ||
| kind | No | ||
| agent | No | ||
| title | Yes | ||
| episode | No | ||
| project_id | Yes | ||
| source_label | Yes | ||
| source_excerpt | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It usefully discloses that proposed items require human review and that this tool cannot approve, replace, or publish memory, but it omits permissions, side effects, and what happens to the proposal after submission.
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?
Two tight sentences, front-loaded with the core action, no repetition or filler. Every clause contributes to the definition.
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?
Given 8 undocumented parameters, no annotations, and no output schema, the description is too thin. It establishes intent and one boundary but leaves parameter meaning and behavioral details for an agent to guess.
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 there are 8 parameters (including a kind enum, agent, episode, project_id, body, title, source_label, source_excerpt). The description adds no meaning for any parameter beyond a vague 'sourced' hint, so it fails to compensate for the schema 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?
Specifies a concrete verb (Propose) and resource (sourced knowledge item), and clarifies the human-review gate. It does not name a sibling tool to contrast against, but the scope is clear enough to distinguish from read/search tools.
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?
'for human review' implies the intended usage context, and 'Cannot approve, replace or publish' sets a negative boundary. However, no alternative tool or explicit condition for choosing this over search_memory or get_handoff is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.