Skip to main content
Glama

Enrich a list's people

enrich_list
Destructive

Use this when the user wants the missing work email addresses or phone numbers found for the people on a list. Starts a job that fills in what each row lacks and saves it on the rows; it answers with the job at once. A run covers up to maxRows rows (10,000 at most) from offset, so a longer list takes several runs. Charged per value found: an email $0.02 from the package or $0.05 from the waterfall, a phone number $0.05 or $0.10. Values a person already had are free. When the job starts, the most it can cost is held from the balance (up to $0.15 a row), and the rest is released when it ends. maxSpendUsd is the most this job may cost: $100 unless the user states another amount. Never raise it yourself. A job that could cost more is refused, stating the amount, and nothing is held. Company lists are refused. Calling again starts a second job.

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": {
      "listId": "<listId>"
    },
    "name": "enrich_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
findNoWhat to find: a work `email` (the default), a `phone` number, or both (`email_and_phone`).email
listIdYesThe people list whose rows to enrich.
offsetNoHow many of the list's rows, in its order, to skip before the run starts: 0 when left out. Enrich a long list in runs, each with `offset` where the last one ended.
maxRowsNoThe most rows to enrich, from 1 to 10,000. Left out, the job runs over every row up to that many.
providersNoWhere to look: `package` (the default) searches our own data package; `waterfall` searches the package, then a fixed series of further providers. A value's price depends on who found it.package
maxSpendUsdNoThe most this job may cost, in US dollars. Leave it out unless the user stated an amount.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already flag a destructive, open-world, non-idempotent write, and the description goes well beyond them: it discloses the async job model, per-value pricing by provider, the hold-and-release of funds from balance, the $100 default cap, the refusal-with-amount behavior when the cap is exceeded, and that repeated calls spawn duplicate jobs. That is unusually complete behavioral context for a costly mutation.

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?

The when-to-use trigger and the async job statement are front-loaded, and every sentence carries information (cost model, pagination, cap policy, refusals, duplicate-call warning). It is dense and slightly repetitive around pricing versus cost, but there is no filler.

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 takes on the burden of explaining the return ('it answers with the job at once'), and it covers pagination, per-value and total cost, balance holds, refusal modes, and duplicate-call semantics. Nothing an agent needs to call this correctly, or to warn a user about spend, is missing.

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 coverage is 100%, so the baseline is 3, but the description still adds operational meaning: it explains that maxRows caps a run and a long list requires offset-chained runs, and that maxSpendUsd defaults to $100 and must not be raised without the user's instruction. It reinforces the pricing consequence of the providers enum, though it does not add format detail for listId.

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: it 'starts a job that fills in what each row lacks and saves it on the rows' for 'the people on a list'. The list-scoped framing separates it conceptually from person-level enrichment siblings, though no sibling is named explicitly (enrich_people, enrich_person), so an agent must infer that boundary rather than read 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?

It opens with an explicit when-to-use trigger ('Use this when the user wants the missing work email addresses or phone numbers found for the people on a list') and adds real exclusions: company lists are refused, the spend cap must not be raised unprompted, and re-calling starts a second job. It stops short of naming a specific alternative tool for single-person or non-list enrichment.

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.

Resources