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

With readOnlyHint/openWorldHint already covering the safety profile, the description adds substantial non-obvious behavior: per-page size and ordering, cursor direction, billing model ('Costs 1 credit', 'Empty and terminal pages are not charged'), and precision semantics for viewCount and likeCount (rounded display values, null when no reactions). It also discloses where raw data lives (raw.messages[].viewsText, reactions, forward source, link preview) and warns that a post id carries the canonical username rather than the handle requested.

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

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

Dense and mostly front-loaded: content shape first, then pagination mechanics, then caveats about the derived counts, then cost. Nearly every sentence carries distinct information, though the first fragment 'Channel posts.' is a weak lead and the cluster of backticked field names makes the back half read as a data dictionary rather than guidance.

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

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

No output schema exists, so the description must carry return-shape burden, and it largely does: it names the payload fields, the pagination cursor path, the raw container for nested data, and the precision quirks of viewCount/likeCount. It leaves the top-level envelope structure and terminal-page signaling (how an agent detects an exhausted channel) unstated, which keeps it short of complete for a paginated listing tool.

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

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

Schema coverage is 67%, so baseline is 3. The description genuinely enriches the handle parameter with a semantic caveat (canonical usernames differ from the one passed, so join on id) that the schema's format examples do not convey, and it reinforces cursor usage. But cache_max_age is undocumented in both schema and description, and the description never repeats or extends the accepted handle formats, so the coverage gap is only partly compensated.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: it returns one public web-preview page of a Telegram channel's posts, and enumerates what each post carries (text, publish date, views, reactions, forwards, media, link previews). An agent can tell this is a paginated post listing rather than a profile lookup, but the description never names its siblings telegram_channel or telegram_post, so the boundary between them is left implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete pagination procedure: 'Pass the returned cursor to fetch the previous page', newest-first ordering, and 20 posts per page, which is real guidance for repeated invocation. However, it never says when to reach for this tool instead of telegram_channel (channel metadata) or telegram_post (single post), nor any exclusions or prerequisites, so the when-to-use-vs-alternatives question is only implied by the phrase 'channel posts'.

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