audit_logRetrieve the most recent mutating tool audit records, showing file paths and sizes. Use to review recent changes without accessing file contents.
Return the last N mutating-tool audit records (paths and sizes only, never contents).
| Name | Required | Description | Default |
|---|---|---|---|
| count | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.8.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this as read-only, and the description adds important behavioral context: it returns only paths and sizes, never contents, and covers only mutating-tool audit records. This clearly sets expectations about what the agent will and will not receive, going well beyond the annotation alone.
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?
A single, tightly worded sentence that front-loads the verb and resource while adding the critical 'never contents' constraint. Every word earns its place; there is no filler or redundancy.
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?
For a simple read-only tool with one optional parameter and an output schema, the description covers the essential behavior, scope, and safety profile. It is slightly incomplete because it does not mention the sibling audit_search or explain when this recent-list tool is preferable, but nothing needed to call it correctly is missing.
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 the description must carry meaning for the single count parameter. The phrase 'last N' directly conveys that count controls how many records are returned, which is the essential semantic. It does not detail bounds or edge cases, but for one optional integer with a default, this is adequate.
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 states a specific verb ('Return'), a clear resource ('mutating-tool audit records'), and a precise scope ('paths and sizes only, never contents'). It is unambiguous about what the tool does, but it does not explicitly differentiate it from the sibling audit_search, so it misses full marks.
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?
No explicit guidance is given about when to use this tool versus alternatives. The sibling list includes audit_search, which likely overlaps, but the description never mentions it or explains when the recent unfiltered list is preferable. The only clue is 'last N', which implies recency, but no when/when-not guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.