Skip to main content
Glama

vokse

by ai.vokse
OverviewDiscussionsAdmin

Payee category hints

payee_category_hints
Read-only

Category evidence per payee, for categorising, in ONE call: name, defaultCategoryId, topCategoryId + topCategoryCount (the category this household used most for the payee), lastCategoryId (its most recent category) and uncategorisedCount (rows still without a category). Fields that are null or zero are omitted; isTransfer: true marks a transfer payee whose rows are never categorised; looksLike ("cash_withdrawal", "bank_fee", "card_payment") marks a payee whose name matches one of the fixed categorising rules (cash withdrawal, bank fee, card payment), which win over its history. When a cash_withdrawal payee is present the result also carries cashAccounts (the open accounts of type cash, by id and name; empty means there is none), cashWithdrawalCategory (the existing cash-withdrawal category, or null) and cashRule, the exact call those rows take: follow it literally. Filter with onlyWithUncategorised: true (the working set of a categorising turn, pending payees first) or payeeIds (up to 200). Use this instead of calling list_transactions per payee: it replaces the same-payee history lookup for every payee at once.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
payeeIdsNoOnly these payees, ids from list_payees.
householdIdNoHousehold ULID to act on. Call list_households for the covered households; may be omitted only when the connection covers exactly one.
onlyWithUncategorisedNoOnly payees that still have uncategorised transactions.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / onlyWithUncategorised / description
      Added value: +"Only payees that still have uncategorised transactions."
    • addedInput schema / properties / payeeIds / description
      Added value: +"Only these payees, ids from list_payees."
  2. First observed

TDQS

A4.9/5.0
Behavior5/5

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

The description discloses behaviors beyond the annotations: null or zero fields are omitted, isTransfer marks never-categorised payees, looksLike fixed rules win over history, and cash_withdrawal payees trigger additional fields plus a literal cashRule. The readOnlyHint already covers safety, and the description adds rich operational detail without contradicting it.

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?

The description is long but dense and well-organized; every clause introduces a distinct behavioral fact or filter. It front-loads the core purpose and then layers edge cases and usage guidance without redundancy.

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

Completeness5/5

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

With no output schema, the description fully covers the return shape, edge cases, filter semantics, and the relationship to a sibling tool. An agent has enough information to select the tool and invoke it correctly.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3. The description adds useful semantic context for onlyWithUncategorised as the working set of a categorising turn and notes the payeeIds bound, but the schema already documents the parameters well.

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?

The description states a specific verb and resource: it provides per-payee category evidence in one call and enumerates the exact fields returned. It also distinguishes itself from sibling list_transactions by explicitly saying it replaces the same-payee history lookup for every payee at once.

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

Usage Guidelines5/5

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

It gives explicit usage context: use it for categorising instead of calling list_transactions per payee. It also clarifies when filters apply, such as onlyWithUncategorised for a categorising turn's working set and payeeIds up to 200.

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

All vokse toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources