mailbox-mcp

list_agent_inbox

Read-onlyIdempotent

Deprecated: use search_inbound_items. Still served unchanged during the alias window. List/search current assigned postal mail using the same /v1/agent-inbox service.

Instructions

Deprecated: use search_inbound_items. Still served unchanged during the alias window. List/search current assigned postal mail using the same /v1/agent-inbox service. q is literal AND search of IDs, stored metadata and authorized stored OCR (NFKC/lowercase, max 200 characters and 12 terms), before pagination; nonempty q additionally needs agent.read. When indexed-source reads are enabled for the account, indexed search includes saved exterior and requested-content pages, including later sample captures. Optional received_after (inclusive) and received_before (exclusive) require that rollout and both read scopes; they filter the stored intake timestamp, never a date guessed from a letter. Sender/address keywords use q and OCR evidence, not an invented sender field. Returns metadata, not text. No fuzzy search or new OCR. Sandbox sees isolated fixtures and enabled assigned member samples; Live sees approved assigned private mail. Read selected matches using get_agent_inbox_sources after indexed rollout, not the original sample /context. Follow pagination.next_offset only while <=10000; narrow query/date windows before exceeding the cap and report incomplete results. Required scopes: agent.inbox.read. Agent-scoped bearer key required; member/facility keys cannot impersonate an agent. Rollout switches, current member approval, assignment, credential environment and SQL authorization are shared with REST. Never substitute another key or mail API after denial.

Input Schema

TableJSON Schema

Name	Required	Description
`q`	No	Literal AND search: every term (max 12, 200 characters, NFKC-normalized and lowercased) must appear in the reference, the sender line or the OCR text of a readable page. Not fuzzy; punctuation is literal.
`limit`	No	Page size, 1–50 (default 25).
`offset`	No	Items to skip, 0–10000 (default 0). Advance by the number returned while more remain; results are a current view, not a snapshot.
`received_after`	No	Inclusive intake time (ISO 8601 with offset): when the facility logged the item, never a printed date.
`received_before`	No	Exclusive intake time (ISO 8601 with offset); must be after received_after.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.0.3Oct 12, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Despite annotations covering read-only safety, the description adds extensive behavioral context: scope requirements for q and date filters, rollout dependencies, sandbox versus live data differences, pagination cap and incomplete-result reporting, and credential enforcement rules. This far exceeds what annotations provide.

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 description is long but front-loads the critical deprecation notice and alternative tool before detailing search semantics, scopes, and pagination. Most sentences carry necessary operational constraints, though the lack of formatting makes it denser than ideal.

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?

Given the tool's complexity—deprecated alias, multiple scopes, rollout conditions, sandbox/live differences, and pagination limits—the description covers everything an agent needs to invoke it correctly. Since an output schema exists, return value details are appropriately left out.

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 descriptions already document all five parameters thoroughly, but the description adds meaningful constraints not present in the schema: nonempty q additionally requires agent.read, and received_after/received_before require the indexed rollout plus both read scopes. It also reinforces that date filters target the stored intake timestamp, never a guessed letter date.

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?

The description explicitly states the tool lists/searches current assigned postal mail and names the preferred alternative search_inbound_items. It distinguishes itself from that sibling by noting its deprecated alias status and unchanged behavior during the alias window.

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

Usage Guidelines5/5

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

It directly says 'Deprecated: use search_inbound_items' and explains the tool still works during an alias window, giving clear when-not and alternative guidance. It also directs users to get_agent_inbox_sources for reading selected matches and warns against substituting another key or mail API after denial.

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

Deploy Server