tg-archive

Overview Schema Source Related Servers Discussions Admin

search_posts

Search archived Telegram posts using hybrid keyword and semantic queries, then filter results by channel, date, topic, post type, hashtag, or availability.

Instructions

Hybrid keyword + semantic search over all archived posts.

query: natural-language or keyword query (any language; exact names like "Qwen3" or arXiv ids work too).
channels: restrict to these channel usernames.
since / until: ISO dates, e.g. "2026-09-01" (until is exclusive).
topics: any-of filter, values from list_topics().
kind: one post type from list_topics() (e.g. model-release, tool-release, paper, tutorial, humor).
hashtags: any-of filter on the author's own hashtags, e.g. ["text2video", "gaussian"] (very precise).
availability: any-of filter, e.g. ["open-weights", "code-only"] for things you can run locally.
Returns posts with date, channel, summary, topics, links, text snippet and permalink.

Input Schema

Name	Required	Description	Default
`kind`	No
`limit`	No
`query`	Yes
`since`	No
`until`	No
`topics`	No
`channels`	No
`hashtags`	No
`availability`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 30, 2026

TDQS

A3.9/5.0

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 does disclose exclusive-until semantics, cross-language query handling, and the returned fields. It says nothing about the default/limit result cap, ranking or ordering, or pagination behavior, which matter for a search tool.

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?

Front-loads the one-line purpose, then a tight per-parameter list, then the return shape. Nearly every line carries information an agent cannot get from the schema.

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 9 parameters, zero schema descriptions, and an output schema that covers return values, the description is close to sufficient. The only real hole is `limit` and result-cap behavior.

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 8 of 9 parameters: it gives the semantics (any-of vs single value), formats (ISO dates, until exclusive), valid-value sources (list_topics), and examples ('Qwen3', arXiv ids). The `limit` parameter is not addressed at all.

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?

Opens with a specific verb and resource plus the retrieval method: 'Hybrid keyword + semantic search over all archived posts.' That is clearly distinct from get_post (single item) and recent (latest feed), though no sibling is named explicitly.

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?

Explains what each filter is for and when to prefer it ('hashtags ... very precise', 'availability ... for things you can run locally'), and routes to list_topics() for valid values. It does not state when to use this instead of `recent`, leaving that to inference.

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

Deploy Server