Skip to main content
Glama

Find files

files_list
Read-onlyIdempotent

The account's files, each with its title, tags, type, correspondent, document date, fields, text status and a fresh download link; newest first unless sort says otherwise (added, document_date, title). Filters: name_contains (name or title), words (in the file's text, every one; scans once read), tags (all of them, or any with tags_match "any"), untagged, document_type, correspondent, the document date from-to, fields ([{field, value | min | max | empty}]: text and links contain the value, numbers, money and dates match it or fall in min-max), has_text (true: Conecto has its words; false: not, e.g. scans not read yet), source (email for email-in). An export's parts show only to the key that made the export and to the owner's and admins' own keys that neither only read nor only draft. Free.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "files_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoadded
tagsNo
limitNo
orderNo
wordsNoWords in the file's text.
fieldsNo
offsetNo
sourceNo
date_toNoDocument date on or before, YYYY-MM-DD.
has_textNo
untaggedNo
date_fromNoDocument date on or after, YYYY-MM-DD.
link_hoursNoHow long the download link works, in hours (up to 168, one week).
tags_matchNoall
correspondentNo
document_typeNo
name_containsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, so the description earns credit for what it adds: download links are freshly minted and time-limited, results are newest-first by default, 'Free' signals no quota cost, and the export-parts visibility rule discloses a non-obvious access constraint. That access sentence is dense and partly opaque, keeping it below 5.

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

Conciseness3/5

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

Zero filler, but it is one semicolon-chained mega-sentence bundling return shape, sorting, eleven filters and a permissions clause. Front-loading is good; parseability suffers and a bulleted or sentence-per-group layout would read far better.

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?

No output schema exists, so the description must describe results and it does (enumerated fields plus a live download link). Filter coverage is broad for a 17-param tool; pagination (limit/offset) and the sort/order interplay are the only real omissions.

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?

With only 24% schema description coverage across 17 params, the description carries most of the load and does: name_contains matches 'name or title', fields supports value/min/max/empty with type-specific matching, has_text is defined both ways, source names 'email'. sort/order, limit, offset and link_hours are only implied or deferred to the schema, so not a full 5.

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?

Opens with a specific verb+resource ('The account's files') and immediately spells out the returned shape (title, tags, type, correspondent, document date, fields, text status, download link) plus default ordering. An agent can tell this is a listing/search tool, not files_get or files_read_text, without opening the schema.

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?

Filter semantics double as usage guidance: 'has_text false: not, e.g. scans not read yet' tells the agent when to use it as a work-queue query, and 'words ... scans once read' signals a prerequisite on prior OCR. There is no explicit when-not or named alternative (e.g. files_get for one file), which keeps it out of the 5 tier.

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