Skip to main content
Glama

Export contacts as CSV

export_contacts_csv
Read-onlyIdempotent

The site's CRM contacts as one CSV — the same file the Contacts screen's Export button downloads: name, email, phone, company, job title, status, lead score, source, tags, created and last-contacted dates. Only this site's contacts; deleted ones are left out. Filter by status or a search on email, name or company. Formula-like cells are neutralised for spreadsheets. truncated is true when more contacts matched than max_rows. PERSONAL DATA — hand the file only to the user who asked for it; never put it in site content or send it anywhere they did not ask for.

Input Schema

NameRequiredDescriptionDefault
searchNoCase-insensitive match on email, name or company
statusNoOnly contacts with this CRM status (e.g. "new", "qualified")
site_idYesThe site, from list_sites
max_rowsNoMost rows to include, default 1000, max 2000
user_goalNoOptional: the user's goal behind this call, in one short sentence of plain words (e.g. "add a page so customers can book tables"). No names, emails or other personal details.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / user_goal
      Added value: +{
      +  "description": "Optional: the user's goal behind this call, in one short sentence of plain words (e.g. \"add a page so customers can book tables\"). No names, emails or other personal details.",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behaviour: exact column set, exclusion of deleted contacts, formula-cell neutralisation for spreadsheets, and the `truncated` signal when matches exceed `max_rows`. The PERSONAL DATA directive goes beyond any structured field and is exactly the kind of handling constraint an agent needs.

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?

Front-loads what the tool produces and what the file contains before the filtering and safety notes. Every sentence carries payload — columns, scoping, filters, sanitisation, truncation, data handling — with no restatement of the name or title.

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?

With no output schema, the description steps in to describe the returned file's contents and the `truncated` field, which covers most of what the agent needs. It does not say how the file is surfaced (attachment, URL, or path), which is the one remaining gap for a file-export tool.

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; the description earns more by explaining the consequence behind `max_rows` (the `truncated` flag) and by restating that `search` spans email, name and company. It leaves `site_id` and `user_goal` to the schema, which is acceptable at full coverage.

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 ('export the site's CRM contacts as one CSV') and anchors it to the known UI behaviour ('the same file the Contacts screen's Export button downloads'), so the agent knows exactly what artifact it gets. Listing the exact columns further disambiguates it from list_contacts or export_submissions.

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 clear operating context — filterable by `status` or `search`, site-scoped only, deleted contacts excluded — and states the personal-data handling rule. It stops short of naming an alternative (e.g. list_contacts for browsing) or an explicit when-not-to-use, which keeps it below a 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.

Resources