herald

Overview Schema Source Related Servers Discussions Admin

send_file

Send a local file or image to a Telegram topic with a concise HTML caption. Automatically delivers small images as photos and other files as documents while respecting allowed file paths.

Instructions

Send an explicitly requested local file or image with a concise caption.

The path must resolve under files.allowed_roots. kind=auto sends supported, small images as Telegram photos and everything else as documents. Use raw Telegram HTML in an HTML caption and keep it within the 1024-character limit.

Input Schema

TableJSON Schema

Name	Required	Default
`kind`	No	auto
`path`	Yes
`agent`	Yes
`model`	Yes
`route`	No
`format`	No	html
`caption`	Yes
`project`	Yes
`subject`	Yes
`reply_to`	No
`reference`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.8.0Sep 25, 2026

addedInput schema / $defs

Added value: +{
+  "InboxMessageKey": {
+    "properties": {
+      "chat_id": {
+        "title": "Chat Id",
+        "type": "integer"
+      },
+      "message_id": {
+        "title": "Message Id",
+        "type": "integer"
+      }
+    },
+    "required": [
+      "chat_id",
+      "message_id"
+    ],
+    "title": "InboxMessageKey",
+    "type": "object"
+  }
+}

addedInput schema / properties / reply_to

Added value: +{
+  "anyOf": [
+    {
+      "$ref": "#/$defs/InboxMessageKey"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

First observedv0.3.0Aug 13, 2026

TDQS

B3.4/5.0

Behavior4/5

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

The description adds meaningful behavior beyond the annotations: path must resolve under files.allowed_roots, kind=auto routes small images as Telegram photos and everything else as documents, and captions have HTML and 1024-character limits. It aligns with readOnlyHint=false and idempotentHint=false and does not imply destructive behavior.

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?

Four compact sentences front-load the primary action and then add only high-value constraints. There is no filler, repetition, or schema duplication.

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

Completeness2/5

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

For a tool with 11 parameters and no schema descriptions, the description leaves essential required metadata fields undefined and does not disambiguate from the sibling send_files. The output schema covers return shape, but invocation context remains incomplete, so an agent would struggle to fill project, subject, agent, and model correctly.

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

Parameters2/5

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

With 0% schema description coverage, the description must compensate, and it does clarify path, kind, and caption semantics. However, six required parameters exist and several of them—project, subject, agent, model—are completely unexplained, along with route, reply_to, and reference, leaving most of the 11-parameter surface opaque.

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?

The description opens with a specific verb and resource: it sends an explicitly requested local file or image with a caption, so an agent can distinguish it from text-only senders like send_text. It does not, however, explicitly contrast it with send_files, send_update, or send_client_copy, so sibling differentiation is incomplete.

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?

The phrase 'explicitly requested' implies when this tool is appropriate, and the description gives useful operational context like files.allowed_roots and kind=auto behavior. However, it never states when to prefer send_file over send_files or send_update, nor does it give any explicit exclusions, so selection guidance is largely left to inference.

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