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

No annotations are supplied, so the description carries the full behavioral burden and largely fails it. It does disclose one behavioral trait — the output is a copy-paste prompt pack with examples rather than a computed report — which is genuinely useful, but it says nothing about whether the tool reads or mutates state, what inputs beyond a free-text query are needed, or how the diagnostic is scoped.

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?

It is short — two sentences — so length is not the problem, but the sentences are loaded with filler adjectives ('production-ready', 'structured, repeatable') that consume space without adding information. The one concrete fact, the prompt-pack deliverable, is buried in the trailing clause rather than front-loaded.

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?

The tool is simple (one optional parameter, no output schema, no annotations), but the description still leaves the core question unanswered: what the diagnostic examines and what the prompt pack contains. For a tool whose only differentiating value is its deliverable, describing that deliverable vaguely is a meaningful omission.

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?

There is a single optional parameter at 100% schema description coverage, so the schema already explains 'Optional user query to scope the analysis.' The description adds nothing about how a query changes the analysis, but with full coverage the baseline of 3 applies.

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 restates the tool name ('sanhao ops diagnostic system') and wraps it in marketing language ('production-ready', 'for marketing and operations leaders') without stating a concrete operation. The only substantive claim is that output arrives 'as a copy-paste prompt pack with examples', which hints at the deliverable but never says what diagnostic the tool actually performs or what it analyzes. It is close to a tautology of the title and gives no basis for distinguishing it from siblings.

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?

There is no guidance on when to invoke this tool, no preconditions, and no mention of alternatives. With near-identical siblings such as restaurant-ops-diagnostic, sanhao-fnb-roi-gate, sanhao-menu-engineering and sanhao-store-site-selector present, the absence of any routing guidance is a serious gap. The phrase 'you can run today' is marketing, not usage instruction.

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