Skip to main content
Glama

normalize_values

Read-onlyIdempotent

Converts and standardizes up to 10,000 values—such as amounts, dates, or phone numbers—to consistent formats and flags invalid or ambiguous entries with reasons.

Instructions

Normalize a list of up to 10,000 values of one kind, e.g. amounts, dates or phone numbers from a document.

kind: auto (inferred like a table column) | number | integer | decimal | date | datetime | boolean | email | url | phone | iban | text. name: optional column name, used as a hint (e.g. 'phone', 'fecha'). Returns one result per input, in order: {"input", "output", "valid"} and "reason" when it could not be converted. Output types: numbers as plain decimal strings, dates ISO 8601, phones E.164.

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": {
      "values": "<values>"
    },
    "name": "normalize_values"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoauto
nameNo
valuesYes
date_orderNo
number_localeNo
phone_countryNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.2/5.0
Behavior3/5

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

The annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, openWorldHint=false), so the description doesn't need to restate those. It does add real behavioral value: the 10,000-value cap, the one-result-per-input ordering guarantee, the input/output/valid shape with a 'reason' on failure, and the concrete output conventions (plain decimal strings, ISO 8601, E.164). It stops short of describing partial-failure behavior or what 'auto' inference falls back to when it can't decide.

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 operation and its limit, then parameters, then return shape — a sensible ordering with almost no filler. The inline kind enumeration is dense but earns its space since the schema omits it. Minor redundancy in restating output formats after already describing the per-value result object.

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

Completeness3/5

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

An output schema exists, so the description's return-value explanation is a bonus rather than a necessity, and the annotations carry the safety profile. The unresolved gap is that three format-control parameters remain unexplained, so an agent cannot reason about how to handle ambiguous locales or date orders from this definition alone.

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

Parameters2/5

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

With 0% schema description coverage the description carries the full burden, and it delivers for only half the parameters. The 'kind' enumeration (auto, number, integer, decimal, date, datetime, boolean, email, url, phone, iban, text) and the meaning of 'name' as an inference hint are genuinely valuable since neither appears in the schema. However, date_order, number_locale, and phone_country receive no mention at all, and these are exactly the knobs an agent would need to interpret ambiguous inputs like 03/04/2025 or 1.234,56 — arguably the highest-risk part of calling this tool.

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

Purpose4/5

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

The description states a specific verb and resource ('Normalize a list of up to 10,000 values of one kind') with concrete examples (amounts, dates, phone numbers) and the kind taxonomy. It does not name or contrast sibling tools such as clean_table or validate_schema, but the operation is distinguishable enough that an agent is unlikely to confuse it.

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

Usage Guidelines3/5

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

Usage is only implied: 'from a document' hints at the source scenario, and 'used as a hint' suggests passing a column name to improve inference. There is no explicit when-to-use, when-not, or comparison against the normalization-adjacent siblings (clean_table, profile_table, validate_schema), leaving the routing decision to inference.

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