Save hours every week. This tax refund calculator toolkit gives you a battle-tested prompt and operating playbook for restaurant/brand growth. No setup, works in any LLM chatbot.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Optional user query to scope the analysis. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full disclosure burden and delivers none: it never says whether the tool computes a result, returns a prompt, requires inputs, or has side effects. The 'save hours' and 'no setup' claims add nothing an agent can act on.
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?
Only three short sentences, but all three are promotional filler rather than specification. Being brief does not earn credit when none of the sentences tell the agent what the tool does.
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 param, no output schema), so completeness should be easy, yet the description never states the actual capability or expected return. Combined with a total mismatch between title domain and described domain, the agent has no reliable basis to invoke it.
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% for the single optional 'query' parameter, so the schema itself documents the only input; per the baseline rule this floors at 3. The description contributes no additional meaning about how a query scopes 'the analysis', but it also creates no confusion about the parameter.
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 name promises a tax refund calculator, but the description pivots to 'a battle-tested prompt and operating playbook for restaurant/brand growth' — a completely different domain. An agent cannot tell whether this computes tax refunds, dispenses F&B marketing advice, or just returns a prompt template, and nothing distinguishes it from the many fnb-* / refund-* 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?
'No setup, works in any LLM chatbot' is marketing reassurance, not usage guidance. There is no statement of when to pick this tool, when not to, or which sibling (fnb-roi-gate, refund-analyze-tool, severance-pay-calculator) covers the adjacent need.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.