Retrieve mistake counts by label, problem tag, platform, and month to spot recurring error patterns and target practice; optionally limit results to recent days.
Mistake counts per label, broken down by problem tag, platform and month. Counts only; reading what they say about the user is up to you.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No |
| Name | Required | Description | Default |
|---|---|---|---|
| kinds | Yes | ||
| by_tag | Yes | ||
| by_month | Yes | ||
| by_platform | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real value by stating the output is aggregate counts with no interpretation supplied, which sets expectations about the return shape. It says nothing about coverage windows, defaults, or empty-result behavior.
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, front-loaded with the aggregation shape and grouping keys. The second sentence is informal but does carry information about the absence of built-in interpretation, so it earns its place.
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?
An output schema exists, so return formatting need not be explained. However, for a tool whose only knob is a time window, leaving `days` (and what null means) undefined is a meaningful gap that the description should close.
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 single parameter `days` is never mentioned in the description at all, even though its null default leaves the time window ambiguous. The 'broken down by ... month' note gestures at time grouping but does not explain the lookback filter.
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 the resource (mistake counts) and the exact grouping dimensions (label, problem tag, platform, month), which tells an agent this is an aggregation tool rather than a record lister. It implicitly contrasts with list_mistakes by being counts-only, but never names that sibling explicitly.
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?
There is no statement of when to reach for this versus list_mistakes, mistake_kinds, or search_problems. The closing phrase ('reading what they say about the user is up to you') hints the tool is for pattern analysis rather than retrieval, but an agent gets no routing rule.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.