tip-splitTip and split: the tip amount, the total, and the per-person share.
| Name | Required | Description | Default |
|---|---|---|---|
| people | No | Number of people (default 1). | |
| tipPct | Yes | Tip in percent. | |
| billAmount | Yes | Bill amount. |
| Name | Required | Description | Default |
|---|---|---|---|
| tip | No | Tip amount. | |
| total | No | Total with tip. | |
| perPerson | No | Per-person share. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true and idempotentHint=true, covering the safety and determinism profile. The description does not add behavioral traits beyond these, such as side effects, auth needs, or rate limits. For a simple calculation tool, no further behavioral disclosure is necessary. The description does not contradict annotations, but it also does not enrich behavioral context.
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 single sentence, front-loaded with the action ('Tip and split') followed by the three outputs. Every word contributes to understanding the tool's purpose. It is concise without missing critical information, and there is no redundancy or fluff.
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 a simple calculator with complete schema coverage, an output schema (not shown but noted as present), and annotations that confirm read-only, idempotent behavior. The description sufficiently communicates the core function and outputs. The only gap is explicit usage guidance, but given the tool's simplicity and uniqueness, the description is otherwise complete for an agent to select and invoke it correctly.
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 100%, with each parameter (billAmount, tipPct, people) having a description. The tool description mentions the outputs (tip amount, total, per-person share) which indirectly relates to the parameters, but it does not add details beyond what the schema provides. It does not clarify values formats, ranges, or default behaviors beyond the schema's 'default 1' for people. Baseline 3 is appropriate given the schema's thoroughness.
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 function: 'Tip and split: the tip amount, the total, and the per-person share.' It identifies the specific outputs (tip amount, total, per-person share) and distinguishes itself from all sibling tools, none of which handle tip calculations. The verb 'split' and the listed outputs make the purpose unambiguous.
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 implies usage: when a user wants to compute a tip or split a bill, this tool is appropriate. However, it does not explicitly state when to use it vs. alternatives, nor does it mention any exclusions or prerequisites. Given the uniqueness of the tool among siblings, the implied usage is clear enough, but explicit guidance is absent.
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.
Many tools are distinct formulas, but there are overlapping families (e.g., future-value, compound-interest, contributions all handle contributions; cagr, required-return, roi all measure returns). The sheer volume of 99 tools increases misselection risk, even with clear descriptions.
All tool names are lowercase with hyphens, following a consistent pattern (verb-noun or noun-phrase). Acronyms like irr, npv, and roa are used predictably. No mixed conventions or camelCase.
99 tools is far beyond the 'extreme mismatch' threshold of 50+. While each calculator is individual, the sheer number makes the server unwieldy and likely to overwhelm agents.
The tool surface covers a wide range of financial calculations: time value of money, loans, bonds, options, depreciation, accounting ratios, FIRE, and German tax specifics. Minor gaps exist (e.g., annuity-due variants, bond yield-to-call), but the core domain is thoroughly addressed.