backup_failure_rca

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

readOnlyHint=true already tells the agent this is a safe read, so the bar is lower. The description adds real value beyond the annotation by disclosing how output is organized (grouped by job, classified by category) and that unknown causes come with sample messages for triage, which shapes how the agent interprets results.

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?

Front-loaded with [READ][RCA] tags, then one sentence of purpose, then the classification list, then a clean Args block. Every sentence earns its place with no 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?

With no output schema, the description compensates by describing the return structure (per-job groups, cause categories, sample messages). Purpose, parameters, and output shape are all covered for a two-parameter read-only tool.

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 coverage is 0% — the schema provides only titles and defaults — so the description must carry the burden, and it does: 'limit' is explained as max recent log entries examined (default 50) and 'target' as a config-derived Xen Orchestra target that defaults when omitted. This adds genuine meaning the schema lacks, though it stops short of format or edge-case detail.

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 (classify) and resource (failed/skipped backup runs), and enumerates the exact output taxonomy (vdi-chain, quiesce, transport, storage-full, unknown). An agent can distinguish this from backup_log_list (raw logs) and backup_job_list (job inventory) without opening a schema.

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 makes the use case clear — triaging recent run failures — and the 'sample messages for triage' note implies a diagnostic context. However, it never states when to prefer this over siblings like backup_log_list, nor any prerequisites or exclusions, so usage is inferred rather than prescribed.

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