Retrieve recent audit records from one node or the whole cluster, with parsed request paths, to inspect activity and trace requests.
Show recent audit records from a node (or all nodes) with parsed request paths.
| Name | Required | Description | Default |
|---|---|---|---|
| node | No | Target cluster node hostname or UUID. Omit for cluster-wide. | |
| context | No | Named login context from ~/.config/sylve/config.yaml. |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully carried by structured fields. The description adds one genuine behavioral detail — records include 'parsed request paths' — which is not in any schema since no output schema exists. It says nothing about record volume, time window, or truncation behind the vague 'recent'.
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 front-loaded sentence with the scope qualifier attached inline; nothing is wasted and nothing important is buried.
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 2-parameter, read-only tool with no output schema, the description should at least convey what the returned records look like and how many/over what period. 'Recent' and 'parsed request paths' gesture at this but leave the return shape and time window undefined.
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 100% and both parameters are documented there, including the 'omit for cluster-wide' behavior and the config file path for context. The description only restates the node/no-node distinction and adds nothing about the context parameter. Baseline 3 is appropriate.
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 ('Show recent audit records') and adds the scope qualifier 'from a node (or all nodes)'. It is distinguishable from the sibling log tools (sylve_vm_logs, sylve_jail_logs) by resource, though it never explicitly names them.
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 parenthetical '(or all nodes)' implies the cluster-wide fallback, but that is already spelled out in the schema's node description. There is no explicit when-to-use vs. alternatives guidance or advice on which sibling log tool to pick.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.