accounting_preview_closePreviewClose computes the per-currency revenue/expense totals and the net income a close would roll, without writing anything. Read-only.
| Name | Required | Description | Default |
|---|---|---|---|
| basis | No | ||
| endDate | No | ||
| companyId | Yes | UUID value wrapper. | |
| startDate | No |
| Name | Required | Description | Default |
|---|---|---|---|
| previews | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds the behavioral detail that it computes per-currency totals and net income, but does not disclose prerequisites, rate limits, or other side effects. This modest addition beyond annotations warrants a 3.
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 brief and front-loaded, stating the core computation first. However, 'without writing anything' and 'Read-only' are redundant, making the second sentence slightly repetitive. It is still efficient and well-structured.
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?
While the output schema exists, the tool description leaves parameter semantics unexplained, particularly startDate, endDate, and basis, which are essential for correct invocation. The high-level overview does not compensate for the low schema coverage, making the tool contextually incomplete.
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 only 25%, with companyId receiving a minimal 'UUID value wrapper' description and basis, startDate, endDate lacking any descriptions. The tool description does not explain the meaning of the date range or basis enum, leaving the agent without enough information to populate these parameters correctly. It fails to compensate for the sparse schema.
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 computes per-currency revenue/expense totals and net income a close would roll, using a specific verb and resource scope. It explicitly distinguishes itself from sibling tools like accounting_close_period by stating 'without writing anything' and 'Read-only', clarifying this is a non-mutating preview.
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 clearly implies the use case: previewing the financial impact of a close before executing it. While it does not explicitly name alternatives, 'without writing anything' contrasts with actual close tools, providing clear context. No explicit when-not-to-use scenarios are given, but the intent is apparent.
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.
Multiple tool pairs are nearly identical (formation_extract_cap_table / formation_extract_cap_table_ocr; formation_start_formation / formation_create_formation), and several tools lack descriptions, making selection ambiguous. The scale of 202 tools with overlapping summaries (e.g., multiple cap-table summary tools) compounds the confusion.
Dominant snake_case `module_verb_noun` pattern, but with notable deviations: `captable_send_safe_for_signature` uses an inconsistent abbreviation, `check_company_name_availability` lacks a module prefix, and `get_list_` vs `list_` prefixes are mixed. Readable but not fully consistent.
202 tools is far beyond any reasonable surface for a single server, even a broad platform. The sheer number overwhelms and makes tool discovery impractical; many tools are peripheral (ads metrics) to the core formation purpose.
The domain appears well covered: formation flows, cap-table lifecycle (import, close, simulate), accounting (journal entries, periods, schedules), cards, documents, and transactions all have CRUD or lifecycle operations. Minor gaps exist (e.g., no card deletion, no counterparty creation), but they are unlikely to cause dead ends.