Skip to main content
Glama

codat

by io.usefulapi

List direct costs

codat_list_direct_costs
Read-only

List a company's direct costs (point-of-sale purchases: card/cash spend, refunds) for a data connection. NOTE: this endpoint is CONNECTION-scoped. Codat API: GET /companies/{companyId}/connections/{connectionId}/data/directCosts. Returns the paged envelope.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoPage number (default 1).
queryNoCodat query filter string, e.g. "status=Paid" or "modifiedDate>2026-01-01". See docs.codat.io/using-the-api/querying.
orderByNoField to order results by, e.g. "-modifiedDate" (leading "-" for descending).
pageSizeNoRecords per page (1-2000, default 100).
companyIdYesThe Codat companyId (UUID).
connectionIdYesThe Codat connectionId (data connection UUID) within the company.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4/5.0
Behavior3/5

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

Annotations include readOnlyHint=true, and description adds 'Returns the paged envelope' beyond schema. However, no additional behavior like data freshness or rate limits disclosed; acceptable for a read tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences that are front-loaded with purpose and include critical scope note. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers purpose, scope, resource type, API endpoint, and return format. Missing output schema but 'paged envelope' suffices. Fairly complete for a simple list tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema descriptions cover all 6 parameters completely, so description adds no new parameter info. Baseline 3 appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly defines the tool as listing direct costs with specific examples (point-of-sale purchases, card/cash spend, refunds). Distinguishes from sibling tools like list_invoices or list_payments by focusing on direct costs and noting connection-scoping.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides clear context: connection-scoped and returns paged envelope. No explicit when-to-use or alternatives guidance, but the resource name and examples imply its niche among siblings.

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

All codat toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0
Disambiguation5/5

Each tool targets a distinct resource or action (e.g., companies, connections, invoices, financial statements). Even similar-looking tools like the three financial statements are clearly differentiated by their names and descriptions. No overlapping purposes.

Naming Consistency5/5

All tools follow the consistent pattern 'codat_verb_noun' (e.g., codat_create_company, codat_list_invoices, codat_get_balance_sheet). No mixing of styles or irregular naming.

Tool Count5/5

28 tools cover the main read and refresh operations across Codat's domain (companies, connections, accounting data, integrations). The count feels well-scoped for a data aggregation platform, not excessive.

Completeness3/5

The tool set focuses heavily on reading and listing data, with only create for companies/connections and refresh triggers. Missing update/delete for many entities (e.g., invoices, bills). An escape hatch exists but is GET-only. Notable gaps for write workflows.

Resources