MailGlass

list_messages

List messages of an inbox, newest first, with built-in extraction results embedded. Pass nextCursor as before to fetch the next page. With filter.from/subject, the server scans only the newest 100 messages before substring-filtering — matches beyond that require paging with before. An empty result with a non-null nextCursor means more pages exist (do not stop on partial pages).

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": {
      "inboxId": "<inboxId>"
    },
    "name": "list_messages"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Default 25.
`before`	No	Keyset cursor (received_at ms) from nextCursor — fetch the next page.
`filter`	No
`inboxId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses ordering, the implicit 100-message cap on filtered scans, the keyset pagination contract, and the empty-page-with-cursor edge case. It omits permissions/auth and whether message bodies are returned in full, which keeps it from a 5.

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?

Four dense sentences, front-loaded with purpose and ordering, then pagination rules. The phrasing 'Pass nextCursor as before' reads ambiguously (parameter name 'before' vs. the adverbial 'as before'), which slightly hurts clarity.

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?

There is no output schema, so the description must hint at returns; it does by naming embedded extraction results and the empty-result/nextCursor shape. It still doesn't say what message fields come back, which is a minor gap for a listing 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 50%, and the description compensates by explaining the before/nextCursor relationship and the substring-filter scan window — semantics absent from the schema. However, inboxId is undocumented in both places, leaving one required parameter unexplained.

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 ('List messages of an inbox'), plus non-obvious scope details: ordering ('newest first') and that extraction results are embedded. That distinguishes it clearly from get_message and list_inboxes without opening a 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?

Gives concrete operational guidance for pagination (pass nextCursor as before), explains the 100-message scan limitation when filter.from/subject is used, and warns not to stop on empty partial pages. It does not name sibling alternatives such as get_message for full message retrieval, so it falls short of a 5.

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

All MailGlass tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?