Retrieve recent Millumin feedback messages, filtered by a case-insensitive substring or time window, to inspect OSC-driven actions and properties.
Return recent feedback messages from Millumin (addresses start with /millumin), optionally filtered by a case-insensitive substring such as "launchedColumn" or "layer:Intro".
| Name | Required | Description | Default |
|---|---|---|---|
| pattern | No | ||
| sinceSeconds | No | Only messages from the last N seconds |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden: it does disclose that matching is case-insensitive and that addresses are namespaced under /millumin, which is genuine added context. However it omits whether reads are non-destructive, whether messages accumulate or are consumed, ordering, and any result-count limit — all relevant for a feedback-buffer read.
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?
One sentence, front-loaded with the action and resource, with the optional filter trailing. The parenthetical examples are useful rather than padding; no wasted prose.
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 no output schema and no annotations, the description should say something about what a returned message looks like (timestamp, address, value) or how many come back. It covers input-side filtering adequately but leaves the response shape entirely unspecified.
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 50%, and the description compensates for the undocumented `pattern` parameter by specifying case-insensitive substring semantics plus two concrete example values. `sinceSeconds` is already documented in the schema, so the remaining gap is minor.
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 and resource (return recent feedback messages from Millumin) and narrows scope to /millumin-prefixed addresses. It does not distinguish itself from the sibling millumin_query, which plausibly also reads Millumin state, so an agent may hesitate between the two.
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?
Usage is implied by the filtering examples ("launchedColumn", "layer:Intro"), which show the kinds of things to search for, but there is no explicit statement of when to prefer this over millumin_query or millumin_ping, nor any exclusion guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.