Get Backup Stats

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds significant context beyond the readOnly/idempotent annotations: it defines 'stale' precisely (last backup attempt, not success), explains that Oxidized does not expose last successful backup time, notes that run history is in-memory and resets on restart, and warns that a node may briefly show as never backed up right after trigger_node_backup. These are critical behavioral quirks an agent must know to interpret results correctly.

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?

The description is a bit long but every sentence carries useful information. It is front-loaded with the core summary, then explains the stale definition and important caveats. While it could be trimmed slightly, the length is justified by the need to convey data-source limitations and behavioral quirks. No wasted words.

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?

Given the tool's complexity (multiple optional filters, nuanced data-source limitations) and that an output schema exists, the description covers all essential context: data source, what counts are computed, the stale definition, and known edge cases (after trigger_node_backup). The output schema handles return format, so no need to describe it. An agent has everything needed to call it correctly and interpret results.

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%, so all four parameters are fully documented in the schema. The description does not add parameter-specific details beyond what the schema provides; it only mentions 'optionally limited to one group or model' and clarifies the stale threshold concept, which is already in the schema. Baseline of 3 is appropriate since the schema does the heavy lifting.

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 clearly states the tool's purpose: 'Summarise backup health across Oxidized nodes.' It specifies the exact resource (backup health across nodes) and the action (summarise). It also lists the specific outputs (counts, success rate, lists of failed/never/stale nodes), distinguishing it from sibling tools that handle node listing, config retrieval, or backup triggering.

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 description implicitly tells the agent when to use this tool: when backup health metrics are needed, explicitly noting that oxidized-web's own stats JSON is not usable. It does not name alternatives or give explicit when-not-to-use conditions, but the unique purpose among siblings makes the usage context clear. It also explains filtering by group/model, giving a sense of optionality.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.