get_checksReturns Layer 3 sanity-check and validation prompts — the 'where AI gets financial modeling wrong' guidance. Use these to audit AI-generated work or catch common modeling errors.
| Name | Required | Description | Default |
|---|---|---|---|
| template_name | Yes | The template to get checks for. Use "all" for universal checks only. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / template_name / enumPrevious value: -[
- "standard",
- "cap_table",
- "venture_fund",
- "runway",
- "all"
-]New value: +[
+ "standard",
+ "cap_table",
+ "venture_fund",
+ "venture_fund_quarterly",
+ "runway",
+ "saas",
+ "ecommerce",
+ "unit_economics",
+ "fund_economics",
+ "fund_economics_tool_web",
+ "venture_valuation",
+ "all"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true and openWorldHint=false, so the safety profile is known. The description adds context about the content's purpose but does not disclose additional behavioral traits such as output format or pagination, meaning it only moderately adds value beyond annotations.
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?
Two sentences, front-loaded with the primary function, followed by a concise use case. Every word adds value, with no redundancy or filler.
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?
For a simple read-only retrieval tool with one fully described parameter and clear usage guidance, the description is complete. No output schema exists, but the description explains what is returned ('prompts') and their purpose, so the agent has enough context to select and invoke 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 description coverage is 100%, with template_name fully documented including the enum and the special 'all' case. The description adds no extra parameter-level information, so it meets the baseline but does not exceed what the schema already provides.
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?
Description uses specific verb 'Returns' and resource 'Layer 3 sanity-check and validation prompts', immediately stating the tool's function. It also clarifies the intended use ('audit AI-generated work or catch common modeling errors'), which differentiates it from siblings like get_prompts or get_best_practices.
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 explicitly states when to use the tool ('Use these to audit AI-generated work or catch common modeling errors'). It does not list alternative tools or exclusions, but the use case is clear enough to guide selection.
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.
Each tool has a distinct purpose: three compute tools for different financial models, two list tools for discovery, and several get_* tools for retrieving context, concepts, prompts, checks, and access info. The get_* tools are numerous but their descriptions clearly differentiate them.
Naming convention is mixed: compute tools use noun_verb (cap_table_compute, exit_waterfall_compute), while access tools use verb_noun (get_access, list_models). This is still readable and somewhat predictable, but not uniform.
11 tools is well within the typical 3-15 range and appropriate for the server's purpose of financial modeling, covering both computation and supporting documentation/discovery without excess.
The compute tools cover the core cap table, exit waterfall, and fund economics models, and the supporting tools provide extensive educational and validation resources. However, list_models suggests more model engines may exist, but only three compute tools are exposed, leaving minor gaps.