Reflecto

This connector has been deprecated

This connector has been replaced by Reflecto.

Send file

send_file

Save a text file to the user's phone Downloads folder. Use this when the user asks you to write something out for them to keep on their phone — notes, a generated report, code, a log — rather than just replying inline. The file is delivered via Reflecto's servers: the content briefly passes through Reflecto in plaintext before being encrypted to the phone (this is NOT end-to-end encrypted, unlike device-to-device mirroring). Content is capped around 128KB — well under what a person would call a large file, since the whole file must be sent as this call's argument.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`content`	Yes	UTF-8 text content of the file. Non-empty, at most 128KB (server-enforced) — the practical ceiling is far lower, since this tool call must carry the whole file as an argument.
`filename`	Yes	Destination filename, written into the phone's Downloads folder. Must end in an allowed plain-text/code extension (server-enforced) — never .html/.svg, which render and execute if tapped.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`byte_length`	Yes	UTF-8 byte length of the content that was sent.
`document_id`	Yes	Server-minted document id.

TDQS

A4.5/5.0

Behavior5/5

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

The description discloses important non-obvious behavior beyond the annotations: content passes through Reflecto's servers in plaintext before being encrypted, is NOT end-to-end encrypted, and is capped around 128KB because the whole file must be sent as the call argument. This is valuable context that readOnlyHint and destructiveHint do not provide.

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

Conciseness5/5

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

The description is three sentences with no filler. It front-loads the purpose and use case, then adds the privacy caveat and size constraint—each sentence carries necessary information.

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 two-parameter tool with full schema coverage, an output schema, and annotations, this description is complete. It covers when to use it, privacy implications, delivery mechanism, and size limits, so an agent has everything needed to select and invoke it correctly.

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

Parameters3/5

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

Schema coverage is 100%, and the schema already documents filename extension restrictions, UTF-8 content, non-empty requirements, and the 128KB limit. The description restates the size cap but adds little new parameter-level meaning beyond what the schema provides.

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 states a specific verb and resource: 'Save a text file to the user's phone Downloads folder.' It also distinguishes the tool from inline replies and from the unrelated sibling tools by specifying the exact scenario it is for.

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?

It gives explicit when-to-use guidance: 'Use this when the user asks you to write something out for them to keep on their phone — notes, a generated report, code, a log — rather than just replying inline.' It also implies when not to use it via the size cap and the non-E2EE warning, though it does not name a specific alternative tool.

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

All Reflecto tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.5/5.0

Disambiguation5/5

Each tool targets a distinct action: scheduling vs cancelling reminders, pushing vs ringing a phone, sending vs receiving files/shared items, and requesting vs polling approvals. The only close pair, send_notification and remind_me, is clearly separated by immediacy vs future scheduling, and the descriptions reinforce the boundary.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern: cancel_reminder, check_reply, get_shared_items, list_devices, request_approval, send_file, send_notification. Minor possessive forms like find_my_phone and remind_me still fit the imperative verb-first style without creating confusion.

Tool Count5/5

Nine tools is well within the ideal range and each one earns its place in a personal-device integration server. The surface covers notifications, reminders, approvals, shared items, file delivery, device discovery, and phone location without redundant or filler tools.

Completeness4/5

Core workflows are covered: reminders can be scheduled and cancelled, approvals can be requested and polled, notifications can be sent, and shared items can be read incrementally. Minor gaps exist, such as no way to cancel a pending approval and no update mechanism for reminders, but these are workable and the server is explicitly stateless about some of them.

Resources

Need Help?