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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the '[read]' prefix adds nothing. The description does add real behavioral context beyond them: lists may have been built from any of the merchant's accounts, one Telegram user counts as exactly one member, and the sending account is chosen later rather than being fixed to the list. It omits return format and pagination behavior, so it is not exhaustive.

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?

The purpose is front-loaded, but the middle is a semicolon-chained explanation of what a list is that could be tightened into one clause. Every idea is relevant, yet the phrasing ('the chat each was seen in (any of the merchant's accounts; one Telegram user is one member)') is dense enough to slow parsing.

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?

With no output schema and 0% parameter coverage, the description partially compensates by specifying the returned fields (name, description, people count) and the account scoping. It leaves pagination semantics (page, per_page defaults of 1 and 50) and the account_id/account_uuid precedence unaddressed, which an agent needs to page results correctly.

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 description coverage is 0%, so the description carries the burden: it explains that account_id / account_uuid scopes results to lists made for that account or for none, which is genuinely non-obvious. However, it never clarifies the relationship between the two identifiers (alternatives? mutually exclusive?) and page/per_page are only defaulted, not explained.

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?

The description names a specific resource (the merchant's saved TG chat lists) and states exactly what each entry carries: name, description and number of people. It also defines the resource concept ('a list is a set of people, the chat each was seen in'), which separates it from a raw member listing. It does not explicitly contrast itself with siblings such as list_tg_list_members or create_tg_list, so it stops short of a 5.

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?

Usage is implied rather than stated: the mention that create_tg_campaign can take a list as its audience tells the agent the downstream consumer but never says 'use this to enumerate candidate audiences before creating a campaign.' There is no when-not guidance and no exclusion relative to the member-level or campaign-level list tools.

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