Retrieve stored project learnings from shared AI memory, filter by project or category, and return compact results to save tokens.
Get learnings. Use compact=True to save tokens.
| Name | Required | Description | Default |
|---|---|---|---|
| compact | No | ||
| category | No | ||
| project_id | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so the safety profile is covered structurally. The description adds the compact/token-saving behavior, a genuine operational note, but says nothing about return format, pagination, or result volume.
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 short sentences with zero padding; the core action is front-loaded and the token hint follows immediately. It is efficient but borders on under-specification rather than genuine conciseness.
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?
With three parameters, no output schema, and no definition of what a "learning" actually is, the description leaves an agent unable to predict what it will receive or how category/project_id shape results. It is not complete enough for a 3-param retrieval tool.
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 category (8-value enum) and project_id are entirely undocumented in the schema. The description clarifies compact's effect but leaves the other two parameters with no semantic guidance, only partially compensating 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?
"Get learnings" simply restates the tool name; it names no scope, no return shape, and does not distinguish this tool from siblings like log_learning, get_context, or search. There is a verb+resource pairing, but it carries no information beyond the identifier itself.
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 only guidance is "Use compact=True to save tokens," which is a parameter tip, not a when-to-use statement. Nothing says when to call this versus get_context, search, or log_learning, and no prerequisites or filters are explained.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.