Skip to main content
Glama

fast-mcp-telegram

Server Details

Multi-tenant Telegram gateway for AI agents — HTTP+stdio, 8 tools, MTProto User API

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL
Repository
leshchenko1979/fast-mcp-telegram
GitHub Stars
47
Server Listing
Fast MCP Telegram

Glama MCP Gateway

Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.

MCP client
Glama
MCP server

Full call logging

Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.

Tool access control

Enable or disable individual tools per connector, so you decide what your agents can and cannot do.

Managed credentials

Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.

Usage analytics

See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.

100% free. Your data is private.
Tool DescriptionsA

Average 4.4/5 across 8 of 8 tools scored.

Server CoherenceA
Disambiguation5/5

Each tool has a clearly distinct purpose: sending, editing, searching chats/messages, retrieving info, and low-level API. The only pair that might seem similar (send_message vs send_message_to_phone) is well-differentiated by targeting chat ID vs phone number.

Naming Consistency4/5

Most tools follow a verb_noun pattern (edit_message, find_chats, get_messages, send_message). Minor deviations: get_chat_info uses an extra noun, send_message_to_phone includes a preposition. Overall consistent snake_case with recognizable verbs.

Tool Count5/5

8 tools is well-scoped for a Telegram messaging server. Each tool covers a fundamental operation without overwhelming the agent. The count aligns with typical MCP server sizes for focused domains.

Completeness4/5

Core messaging operations are covered (send, edit, read, search, chat metadata). Missing delete message and direct contact management, but the low-level invoke_mtproto tool can fill most gaps. Minor gaps remain.

Available Tools

8 tools
edit_messageEdit messageA
DestructiveIdempotent
Inspect

Replace the text of an existing message in a Telegram chat. Only works on messages sent by the authenticated account. Cannot edit media or other message attributes — text only. Success: dict with message_id, date, chat, text, status='edited', and edit_date. Error: dict with ok=false and error string (e.g. message not found or not editable). Use edit_message to update a previously sent message; use send_message to create new ones. Full documentation: https://github.com/leshchenko1979/fast-mcp-telegram/blob/main/docs/Tools-Reference.md

ParametersJSON Schema
NameRequiredDescriptionDefault
chat_idYesTarget chat: numeric id (e.g. -100…), username without @, or 'me' for Saved Messages.
messageYesMessage text. When sending files, used as caption.
message_idYesMessage id in this chat to edit (from get_messages or Telegram).
parse_modeNo'markdown', 'html', or 'auto' (detect from content). Default is 'auto'.auto

Output Schema

ParametersJSON Schema
NameRequiredDescription
okNo
chatNo
codeNo
dateNo
textNo
errorNo
actionNo
paramsNo
senderNo
statusNo
topic_idNo
edit_dateNo
exceptionNo
operationNo
error_codeNo
message_idNo
reply_markupNo
Behavior5/5

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

Adds significant context beyond annotations: authentication requirement, text-only limitation, and detailed return format (success/error dicts). No contradiction with annotations.

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?

Every sentence is informative, front-loaded with purpose, no fluff. Structure logically flows from action to constraints to return to guidance.

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?

Complete for a mutation tool with annotations and output schema. Explains constraints, return values, alternative tools, and links to full docs.

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 covers all 4 parameters with descriptions (100% coverage). Description does not add extra semantic value beyond schema; baseline of 3 is appropriate.

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?

Description clearly states it replaces text of an existing message, specifies constraints (only own messages, text only), and distinguishes from send_message. Uses specific verb+resource.

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?

Explicitly tells when to use (update previous message) and when to use alternative (send_message for new ones). Also notes constraints like only works on own messages.

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

find_chatsFind chatsA
Read-onlyIdempotent
Inspect

Find users/groups/channels by name, username, or phone. Global search (query required) searches all Telegram; with min_date, max_date, or filter, search uses dialog list or a named filter; include_peers filters use last-activity from GetPeerDialogs; flag-based filters use dialog list dates. Success: dict with key chats (list of chat objects). Full documentation: https://github.com/leshchenko1979/fast-mcp-telegram/blob/main/docs/Tools-Reference.md

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum chats to return (recommended 50 or less).
queryNoName, username (no @), phone (+country…), or comma-separated multi-queries. Required for global search unless you use min_date/max_date or folder alone.
folderNoTelegram folder name (case-insensitive exact match after normalization). In Telegram's UI these are called folders; internally they are "dialog filters" — saved filter presets that group chats by custom criteria (pinned, unread, business, etc.). See Filters-vs-Folders.md for the technical distinction.
publicNoIf true, prefer chats with a public username; if false, without. Does not apply to private DMs. Omit to skip this filter.
max_dateNoInclusive maximum date filter (ISO 8601 date or datetime). Omit for no upper bound.
min_dateNoInclusive minimum date filter (ISO 8601 date or datetime). Omit for no lower bound.
chat_typeNoComma-separated chat kinds: private, bot, group, channel. Case-insensitive; extra spaces allowed.

Output Schema

ParametersJSON Schema
NameRequiredDescription
okNo
codeNo
chatsNo
errorNo
actionNo
paramsNo
exceptionNo
operationNo
error_codeNo
Behavior5/5

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

Annotations declare readOnlyHint, idempotentHint, and openWorldHint, indicating safe, idempotent reads. The description adds detail on search modes (global vs dialog list) and how filters work, enhancing transparency beyond annotations.

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 well-structured: first sentence states purpose, second explains search modes, third mentions output and documentation. It is concise with no redundancy, though could be slightly shorter.

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 complexity of 7 parameters and no required ones, the description covers parameter interactions, output format, and provides a documentation link. Output schema exists, so return values are explained. Complete for an AI agent.

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 100%, so description adds value by explaining parameter interactions (e.g., query required for global search, formatting hints like no @). This goes beyond basic schema descriptions.

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 clearly states the tool finds users/groups/channels by name, username, or phone. It distinguishes itself from sibling tools like search_messages_globally (which searches messages) and get_chat_info (which gets specific chat info). The verb 'find' plus resource 'chats' is specific.

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?

The description explains when to use different parameters: query required for global search, min_date/max_date/filter for dialog list, include_peers for specific filters. It does not explicitly exclude alternatives but provides clear context for parameter selection.

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

get_chat_infoGet chat infoA
Read-onlyIdempotent
Inspect

Load profile and metadata for one user, bot, group, or channel. Success: info dict; forum chats may include topics up to topics_limit. Full documentation: https://github.com/leshchenko1979/fast-mcp-telegram/blob/main/docs/Tools-Reference.md

ParametersJSON Schema
NameRequiredDescriptionDefault
chat_idYesTarget chat: numeric id (e.g. -100…), username without @, or 'me' for Saved Messages.
topics_limitNoMax forum topics to list when the chat is a forum.

Output Schema

ParametersJSON Schema
NameRequiredDescription
idNo
okNo
codeNo
errorNo
phoneNo
titleNo
actionNo
is_botNo
paramsNo
topicsNo
is_userNo
is_forumNo
is_groupNo
usernameNo
exceptionNo
last_nameNo
operationNo
error_codeNo
first_nameNo
is_channelNo
topics_has_moreNo
participants_countNo
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds useful behavioral detail about forum topics including the topics_limit parameter, which goes beyond the annotations.

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?

Two concise sentences, no fluff, with a link to full documentation. Every sentence adds value.

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

Completeness4/5

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

Given the simple nature of the tool, schema coverage, annotations, and existence of output schema, the description is complete enough. The link to full docs compensates for any missing details.

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 description coverage is 100% and both parameters have clear descriptions. The description adds minor context about forum topics but no critical additional meaning beyond the schema.

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 clearly states it loads profile and metadata for one user, bot, group, or channel, which is a specific verb and resource. It distinguishes from sibling tools like get_messages (messages) and send_message (send).

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?

No explicit when-to-use or when-not-to-use guidance is provided. The context of sibling tools implies usage, but no exclusions or alternatives are mentioned.

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

get_messagesGet messages in chatA
Read-onlyIdempotent
Inspect

Read or search messages in one chat: browse latest, search text, fetch by ids, or load replies to a message (comments, forum topics, threads). Do not combine message_ids with query or reply_to_id. Success: messages, has_more, optional total_count and discussion fields. Full documentation: https://github.com/leshchenko1979/fast-mcp-telegram/blob/main/docs/Tools-Reference.md

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum messages to return (recommended 50 or less).
queryNoSearch within this chat only; comma-separated terms. Omit to browse latest or use message_ids / reply_to_id modes.
chat_idYesTarget chat: numeric id (e.g. -100…), username without @, or 'me' for Saved Messages.
max_dateNoInclusive maximum date filter (ISO 8601 date or datetime). Omit for no upper bound.
min_dateNoInclusive minimum date filter (ISO 8601 date or datetime). Omit for no lower bound.
message_idsNoExact message ids to fetch. Mutually exclusive with query and reply_to_id.
reply_to_idNoAnchor message id: channel post id, forum topic_id from get_chat_info, or a message id for direct replies. Use with thread_scope.
thread_scopeNoOnly with reply_to_id. auto: full forum topic (topic_id) or channel comment thread via getReplies; else direct replies. full: nested branch under a message id (forum in-topic uses search window, not whole topic); supergroup threads use search top_msg_id. direct: immediate replies only.auto
auto_expand_batchesNoExtra search batches to run when filters narrow results. Higher values may return more matches at the cost of latency.
include_total_countNoIf true, response may include total_count where supported (per-chat search; ignored for global search).

Output Schema

ParametersJSON Schema
NameRequiredDescription
okNo
codeNo
errorNo
actionNo
paramsNo
_warningNo
has_moreNo
messagesNo
exceptionNo
operationNo
error_codeNo
total_countNo
Behavior4/5

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

Annotations declare readOnlyHint and idempotentHint. Description adds behavioral constraints (mutual exclusivity of params) and success response shape (messages, has_more, etc.). No contradiction with annotations.

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?

Concise with a few sentences. Front-loaded with purpose. Could be slightly more structured (e.g., bullet points), but no waste. Good balance.

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 high schema coverage and presence of an output schema, the description is complete. It mentions success fields and links to full docs. No gaps for the tool's complexity.

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 description coverage is 100%, so each parameter already has a description. The description does not add significant meaning beyond what the schema provides; it only mentions success fields. Baseline 3 is appropriate.

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 clearly states the tool reads or searches messages in one chat, listing multiple modes (browse latest, search text, fetch by ids, load replies). It distinguishes from siblings like search_messages_globally (global search) and find_chats (chat listing).

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?

Explicitly states not to combine message_ids with query or reply_to_id. Implies when to use each mode. Provides a link to full documentation. Does not directly compare to sibling tools, but purpose is clear enough to avoid confusion.

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

invoke_mtprotoInvoke MTProtoA
Destructive
Inspect

Low-level Telegram API (MTProto) invoke for methods not wrapped by other tools. Dangerous methods require allow_dangerous=true. Success: API result dict or normalized error. Full documentation: https://github.com/leshchenko1979/fast-mcp-telegram/blob/main/docs/Tools-Reference.md

ParametersJSON Schema
NameRequiredDescriptionDefault
resolveNoIf true, resolve string/int peer-like fields to TL Input* entities before invoke.
params_jsonYesJSON object string of TL parameters as in Telegram API docs; nested TL uses "_": "typeName" discriminator.
allow_dangerousNoIf false, destructive methods (e.g. deletes) are blocked. Set true only when intended.
method_full_nameYesTelegram API method, e.g. "messages.GetHistory" or "users.GetFullUser" (normalization applied).

Output Schema

ParametersJSON Schema
NameRequiredDescription
_No
idNo
okNo
codeNo
dateNo
chatsNo
errorNo
usersNo
actionNo
paramsNo
resultNo
messagesNo
exceptionNo
operationNo
error_codeNo
Behavior3/5

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

Annotations provide destructiveHint and openWorldHint. Description adds return format and safety requirement, but does not elaborate on what specific destructive actions occur or other behavioral traits.

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?

Three sentences, front-loaded with purpose, then critical safety and return info, ending with a documentation link. No redundant text.

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

Completeness4/5

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

Complex low-level tool with output schema and a link to full documentation. Description adequately covers core purpose, safety, and return shape, but could briefly mention error handling specifics.

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% so baseline is 3. Description reiterates 'allow_dangerous' usage but adds little beyond the already descriptive schema definitions.

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 clearly states this is a low-level MTProto invoke for methods not wrapped by other tools, distinguishing it from siblings by targeting uncovered Telegram API methods.

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?

Explicitly mentions that dangerous methods require 'allow_dangerous=true' and implies use when no other tool wraps the method, but does not list specific exclusions or alternatives.

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

search_messages_globallySearch messages globallyA
Read-onlyIdempotent
Inspect

Search all Telegram chats at once (not scoped to one chat). Comma-separated query terms; optional filters by date, chat kind, and public username. Success: message list and metadata dict. Global search ignores include_total_count. Full documentation: https://github.com/leshchenko1979/fast-mcp-telegram/blob/main/docs/Tools-Reference.md

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum messages to return (recommended 50 or less).
queryYesSearch terms, comma-separated for multiple terms (OR-style global search). Required.
publicNoIf true, prefer chats with a public username; if false, without. Does not apply to private DMs. Omit to skip this filter.
max_dateNoInclusive maximum date filter (ISO 8601 date or datetime). Omit for no upper bound.
min_dateNoInclusive minimum date filter (ISO 8601 date or datetime). Omit for no lower bound.
chat_typeNoComma-separated chat kinds: private, bot, group, channel. Case-insensitive; extra spaces allowed.
auto_expand_batchesNoExtra search batches to run when filters narrow results. Higher values may return more matches at the cost of latency.
include_total_countNoIf true, response may include total_count where supported (per-chat search; ignored for global search).

Output Schema

ParametersJSON Schema
NameRequiredDescription
okNo
codeNo
errorNo
actionNo
paramsNo
_warningNo
has_moreNo
messagesNo
exceptionNo
operationNo
error_codeNo
total_countNo
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds value by stating that global search ignores include_total_count and that results return a message list and metadata dict. No contradictions.

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, each adding distinct value: scope, filters, and success format plus a key behavioral note. The link to full docs is a bonus. No wasted words.

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

Completeness4/5

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

Given the tool has 8 parameters, a required one, and an output schema (not shown), the description covers the essential aspects. It mentions the key behavioral note about include_total_count and refers to documentation for completeness. It is adequate for selecting and invoking the tool.

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?

The input schema already provides 100% coverage with detailed descriptions for all 8 parameters. The description summarizes them (comma-separated query, optional filters) but does not add significant new meaning beyond what is in the schema.

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 clearly states the tool searches all Telegram chats globally, setting it apart from per-chat tools like 'get_messages'. It specifies the action ('search'), the resource ('messages globally'), and the scope ('all chats at once') with no ambiguity.

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?

The description implies global search is for broad queries and notes that 'Global search ignores include_total_count', hinting at when not to use it. However, it does not explicitly name alternative tools or provide when-not scenarios, but the context is sufficiently clear for most use cases.

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

send_messageSend messageA
Destructive
Inspect

Send text and optional file attachments to a Telegram chat. Supports reply-to (including forum topics and channel discussion groups), auto-detected or explicit parse_mode (markdown/html), and file attachments as http(s) URLs, local paths, or data: URIs. When files are provided, the message text becomes a caption. For channel posts with reply_to_id, automatically posts in the linked discussion group. Success: dict with message_id, date, chat, text, status='sent', and sender info. Error: dict with ok=false and error string. Use send_message to create new messages; use edit_message to modify existing ones. Use send_message_to_phone when targeting a phone number instead of a chat_id. Full documentation: https://github.com/leshchenko1979/fast-mcp-telegram/blob/main/docs/Tools-Reference.md

ParametersJSON Schema
NameRequiredDescriptionDefault
filesNoList of attachment URLs, local paths, or data URIs (one or more strings). data: URIs (data:<mime>;base64,<payload>) work in all server modes; local paths work in stdio mode only.
chat_idYesTarget chat: numeric id (e.g. -100…), username without @, or 'me' for Saved Messages.
messageYesMessage text. When sending files, used as caption.
parse_modeNo'markdown', 'html', or 'auto' (detect from content). Default is 'auto'.auto
reply_to_idNoTelegram message id to reply to. For forums, topic root id; for channel posts, post id (may create a comment). Omit for a new top-level message.

Output Schema

ParametersJSON Schema
NameRequiredDescription
okNo
chatNo
codeNo
dateNo
textNo
errorNo
actionNo
paramsNo
senderNo
statusNo
topic_idNo
edit_dateNo
exceptionNo
operationNo
error_codeNo
message_idNo
reply_markupNo
Behavior5/5

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

Discloses behaviors beyond annotations: auto-posting in discussion groups for channel posts, success/error response format, local path limitations. Annotations include destructiveHint and openWorldHint, which are not contradicted.

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?

Well-structured with main action first, then details, then usage guidance. Slightly lengthy but each sentence adds value; could be slightly more concise.

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?

Complete for a tool with 5 params, 100% coverage, output schema, and sibling tools. Covers behavior, parameters, and provides reference to full documentation.

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?

Adds context beyond schema: explains that files make text a caption, reply_to_id behavior for forums and channels, parse_mode auto-detection. Schema coverage is 100%, but description enriches meaning.

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?

Clearly states the tool sends text and optional file attachments to a Telegram chat. Distinguishes from siblings edit_message (modify) and send_message_to_phone (target phone number).

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?

Explicitly says when to use: 'Use send_message to create new messages; use edit_message to modify existing ones. Use send_message_to_phone when targeting a phone number.' Also provides documentation link for further details.

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

send_message_to_phoneSend message to phoneA
Destructive
Inspect

Send to a phone number: may create a temporary contact, then send text or files. Success: send result plus contact_was_new / contact_removed when applicable. Full documentation: https://github.com/leshchenko1979/fast-mcp-telegram/blob/main/docs/Tools-Reference.md

ParametersJSON Schema
NameRequiredDescriptionDefault
filesNoList of attachment URLs, local paths, or data URIs (one or more strings). data: URIs (data:<mime>;base64,<payload>) work in all server modes; local paths work in stdio mode only.
messageYesMessage text. When sending files, used as caption.
last_nameNoLast name when creating a temporary contact.Name
first_nameNoFirst name when creating a temporary contact.Contact
parse_modeNo'markdown', 'html', or 'auto' (detect from content). Default is 'auto'.auto
phone_numberYesE.164 phone number with country code, e.g. +1234567890 (must be on Telegram).
remove_if_newNoIf true, delete the contact after send when it was created only for this send.
reply_to_msg_idNoReply to this message id in the target chat after resolve.

Output Schema

ParametersJSON Schema
NameRequiredDescription
okNo
chatNo
codeNo
dateNo
textNo
errorNo
actionNo
paramsNo
senderNo
statusNo
topic_idNo
edit_dateNo
exceptionNo
operationNo
error_codeNo
message_idNo
phone_numberNo
reply_markupNo
contact_removedNo
contact_was_newNo
Behavior5/5

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

Annotations already mark destructiveHint=true and openWorldHint=true. The description adds context about creating temporary contacts and the possibility of removal, plus the structure of the success response (send result + contact_was_new/contact_removed).

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?

Two sentences: first clearly states the core action and side effect, second adds output details and a link to full documentation. No redundant information.

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

Completeness4/5

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

Given the tool's complexity (8 parameters, temporary contact creation, multiple output fields), the description covers the key behavioral aspects and points to full docs. It could elaborate on the temporary contact lifecycle but is sufficient with the output schema present.

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 description coverage is 100%, so the schema already documents each parameter. The tool description does not add additional semantics beyond summarizing the action and output.

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?

Description clearly states the verb 'Send', the target 'phone number', and the effect 'may create a temporary contact, then send text or files'. It distinguishes from sibling tools like 'send_message' which likely target chats.

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?

The description implies when to use this tool (sending to phone numbers rather than chats). It does not explicitly state when not to use or mention alternatives, but the name and context provide sufficient guidance.

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

Discussions

No comments yet. Be the first to start the discussion!

Try in Browser

Your Connectors

Sign in to create a connector for this server.