Skip to main content
Glama
weirdapps

sch-mail

by weirdapps

sch_send_mail

Send a new email via SMTP or save it as a draft by default, with optional CC/BCC, HTML body, and attachments.

Instructions

Send a new email via SMTP, or save as draft (default).

Args: to: Recipient(s), comma-separated (e.g. "a@x.gr,b@y.gr") subject: Subject line body: Email body (plain text by default; set html=True for HTML) cc: CC recipient(s), comma-separated bcc: BCC recipient(s), comma-separated html: True if body is HTML; False (default) for plain text attachments: List of absolute file paths to attach. Each must be an existing file inside the allowed folders (by default ~/Downloads and the temp dirs; SCH_MAIL_ALLOWED_DIRS replaces them). One that is missing or outside them fails the whole call, so nothing is saved or sent without it. send_now: True to dispatch via SMTP immediately. Default False = save to Drafts folder. account: Account key in credentials.json (e.g. "personal" or "work"). Default: the account named by "default" in that file.

Returns dict with status ("draft_saved" or "sent"), folder/recipients, and message id.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ccNo
toYes
bccNo
bodyYes
htmlNo
accountNo
subjectYes
send_nowNo
attachmentsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
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 the atomic attachment-validation rule (missing or out-of-allowed-dir file fails the whole call, nothing saved or sent), the allowed-dirs default and SCH_MAIL_ALLOWED_DIRS override, and account resolution from credentials.json. Auth mechanics and any rate limits are not spelled out, but failure semantics and defaults are unusually well covered.

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?

Purpose is front-loaded in one sentence, then a clean per-argument list where each line earns its place. The attachments entry is long, but that length buys genuinely load-bearing failure-mode information rather than padding.

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?

For a 9-parameter mutation tool with zero schema coverage and no annotations, nothing critical is missing: modes, defaults, attachment constraints, account selection, and failure behavior are all present. The brief return summary ('draft_saved' or 'sent', folder/recipients, message id) is mildly redundant against the output schema but harmless.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% across 9 parameters, so the description must compensate – and it does. It defines formats and examples for every parameter: comma-separated recipient lists with an example ('a@x.gr,b@y.gr'), html's effect on body, attachments as absolute paths with validation rules, send_now's default, and account's default key resolution.

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 ('Send a new email via SMTP') plus the key mode switch ('or save as draft (default)'). The word 'new' implicitly separates it from sch_forward_mail, so an agent can route between the two send-family tools 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 clear operational context: the default is a draft and send_now=True dispatches it, which is the main decision an agent must make. It does not name alternatives or state when-not to use it (e.g. vs sch_forward_mail), so it stops short of full routing guidance.

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