Skip to main content
Glama

Review many

purch_review_batch
Destructive

Review a whole statement in one act: status, category and vendor per row, one reason. Checked whole; refused whole. READ purch_vocabulary FIRST: it holds the statuses and what they mean, and the person's own categories and vendors, which are the words to use. Propose a status, a category and a vendor for every row, show the person the whole table, and write nothing until they have answered. Then write it all in one act with their confirmation as the reason.

Every row marked recurring must carry its vendor (the shop's name, e.g. "Adobe"): naming it is what declares the subscription. A transfer's category is where the money went or came from (checking, savings, the card being paid). Every row is validated before any is written, and the batch is refused whole with the row and the fix named; a row you cannot name stays out of the batch and unreviewed, never guessed. Up to 200 rows. Effects: status, category, vendor recorded on every row listed.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "rows": "<rows>"
    },
    "name": "purch_review_batch"
  }
}

Input Schema

NameRequiredDescriptionDefault
rowsYesThe rows and what they are.
reasonNoWhy — typically "confirmed by the person" plus anything they said.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and readOnlyHint=false but say nothing about atomicity; the description adds that the batch is validated before any write and refused whole with the offending row and the fix named. It also discloses the 200-row ceiling, the all-or-nothing semantics, and the "Effects" line listing exactly what gets recorded per row.

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

Conciseness4/5

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

Front-loaded with the core action and ordered by workflow, and most sentences carry non-obvious rules. Some rhetorical fragments ("Checked whole; refused whole.") and a restatement of the schema's "Required for recurring" cost a little density.

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?

For a destructive batch mutation with no output schema, the definition covers the prerequisite tool, the human-confirmation gate, per-row special cases, validation-failure behavior, the size limit, and the exact effects on records. An agent has everything needed to call it correctly and safely.

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 coverage is 100%, so the schema already documents rows, status, vendor, category, cadence, note, transaction_id and reason; baseline is 3. The description does add real meaning beyond the schema for two fields — vendor naming declares a subscription, and a transfer's category is the account the money moved to or from — but leaves cadence, note and reason largely to the schema.

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?

States a specific verb and resource ("Review a whole statement in one act") plus the exact payload (status, category, vendor per row, one reason) and the scale cap (up to 200 rows). The phrase "a whole statement" and the row cap clearly separate it from the single-row review sibling without needing to name it.

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?

Gives a concrete operating sequence: read purch_vocabulary first, propose for every row, show the whole table, write nothing until the person answers, then write with their confirmation as the reason. It also states an exclusion rule (rows you cannot name stay out of the batch). It stops short of explicitly contrasting with the single-transaction review tool, so 4 rather than 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.