Retrieve locally archived mistakes and rejected answer combinations for review, with optional filtering by question text; returns stored records without inferring corrected keys.
Read complete locally archived mistakes and rejected combinations, without inferring corrected keys.
| Name | Required | Description | Default |
|---|---|---|---|
| question_contains | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v1.9.4Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description does add real behavioral context: the data is local ('locally archived'), the read is exhaustive ('complete'), and no answer-key correction/inference is performed. It omits pagination, ordering, and what happens when the archive is empty.
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 with the read verb front-loaded and no filler, though the phrase 'mistakes and rejected combinations' spends words on jargon instead of a precise noun.
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 shape need not be described. However, for a tool sitting among dozens of exam/review readers, the description lacks the scope and filter semantics an agent needs to call it correctly.
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?
The single parameter question_contains has 0% schema description coverage, so the description carries the full burden — yet it never mentions filtering, substring matching, or that an empty default returns everything. The schema-only baseline of 4 is not earned here.
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 verb 'Read' and the scope 'locally archived' are clear, but 'mistakes and rejected combinations' is domain jargon that never resolves into a concrete resource (exam questions? video questions?). It also fails to distinguish itself from the many sibling readers such as preview_owned_exam_questions and owned_exam_review_inventory.
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 use this tool, when not to, or which sibling to prefer despite a dense cluster of overlapping question-reading tools. The only guidance is a negative qualifier ('without inferring corrected keys'), which constrains output rather than selecting the tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.