Report

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

The description adds genuine interpretive context beyond the annotations — it explains how two data sources are cross-correlated and what a specific combination means (link/aging fault rather than media wear), which matters because there is no output schema. But it never discloses whether invoking the tool has any side effects, latency cost, or privilege requirements, leaving the readOnlyHint=false / idempotentHint=false annotations unexplained for what reads like a passive reporting operation.

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 core content is front-loaded in one sentence, but that sentence is padded with an em-dash interpretive clause and a cryptic trailing reference '(CONCEPT:SM-OS.governance.sys-8/SYS-1.5)' that carries no actionable meaning for an agent. The leading 'Report (sm_storage_health)' opener is close to tautological.

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 and sparse annotations, the description should carry more burden: it does not say what the report returns (text vs. structured, per-disk rows vs. summary), whether SMART megaraid passthrough requires elevated privileges, or how expensive a full poll is. The correlation/interpretation note is a real plus for a diagnostic tool, but the picture is still incomplete for a collector that touches BMC and RAID layers.

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 schema takes no parameters (additionalProperties: false), so there is nothing for the description to disambiguate. Baseline for a zero-parameter tool applies; the description correctly conveys that the tool is invoked without arguments.

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 names the concrete data sources it aggregates (SMART including megaraid passthrough, BMC/IPMI drive-slot faults, RAID physical-disk state), which is far more specific than the title 'Report'. However, it never explicitly states how it relates to the three per-domain siblings (sm_storage_health_smart, sm_storage_health_faults, sm_storage_health_raid), so the agent has to infer that this is the combined/correlated view.

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?

Usage is only implied: the tool is framed as a correlated cross-source report, and the note about a BMC-flagged disk with clean SMART reading as a link/aging fault hints at the whole-picture use case. There is no explicit 'use this when you want all three signals at once, use sm_storage_health_smart when you only need media data' routing, and no prerequisites stated.

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