Skip to main content
Glama
julioc-barros

imap-mail-mcp

by julioc-barros
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

search_emails

Find emails in an IMAP folder by sender, recipient, subject, text, date, or flags. Returns newest matches first with UID, sender, subject, date, and flags.

Instructions

Busca e-mails em uma pasta de uma conta. Retorna os mais recentes primeiro com UID, remetente, assunto, data e flags. account: nome ou e-mail da conta; vazio = conta padrão. Datas no formato YYYY-MM-DD. raw_criteria permite passar critério IMAP SEARCH direto (ex.: 'UNSEEN FROM "x"'), ignorando os demais filtros. Os filtros sender/to/subject/text são substring, case-insensitive.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toNo
textNo
limitNo
sinceNo
beforeNo
folderNoINBOX
senderNo
unseenNo
accountNo
flaggedNo
subjectNo
raw_criteriaNo
larger_than_kbNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.2.1
    • addedInput schema / properties / account
      Added value: +{
+  "default": "",
+  "title": "Account",
+  "type": "string"
+}
  2. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It usefully discloses result ordering ('mais recentes primeiro'), the returned fields (UID, remetente, assunto, data, flags), and that raw_criteria bypasses the other filters. It omits read-only safety framing, pagination/limit behavior, and any cost or rate-limit notes for a 13-parameter search.

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?

Compact and front-loaded: purpose and return shape come first, followed by tightly packed parameter notes. No filler sentences, though the terse 'chave: valor' style compresses some ideas to the point of ambiguity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 13-parameter tool with no annotations and no output schema, the description covers return fields and several key parameters well, but omits the limit/pagination contract and the unseen/flagged/larger_than_kb filters, which an agent cannot infer from the bare schema titles.

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 0%, so the description must compensate, and it does for the highest-value parameters: account default behavior, date format (YYYY-MM-DD) for since/before, substring/case-insensitive semantics for sender/to/subject/text, and the raw_criteria override rule. It leaves limit, unseen, flagged, larger_than_kb, and folder entirely undocumented, but the added semantics still materially exceed the schema.

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?

States a specific verb and resource ('Busca e-mails em uma pasta de uma conta') and describes the return shape. The phrase 'de uma conta' implicitly distinguishes it from the sibling search_all_accounts, but that sibling is never named, so the differentiation is inferential rather than explicit.

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

Usage Guidelines3/5

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

Usage context is only implied: the reader must infer that this searches within one account while search_all_accounts spans accounts. It does clarify an important behavioral rule (raw_criteria overrides other filters), but gives no explicit when-to-use/when-not or prerequisite statements.

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

Deploy Server

Other Tools