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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, and the description's closing 'Read-only' merely restates that. Beyond annotations it does add the per-call ceiling ('at most 20 per call') and, importantly, the shape of each returned record (name, e-mail, phone, consent, source, order count, total spent, last order date, tags) — valuable since there is no output schema, though pagination or ordering behaviour across calls is never addressed.

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?

Front-loaded with the verb and scope, then the field list, then the selectors, then routing advice — a sensible information hierarchy with no filler sentences. It is dense as a single undivided paragraph and the multilingual example queries add bulk a non-Ukrainian-reading agent cannot use, but every other clause earns its place.

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, the description correctly substitutes a record-field enumeration, and it discloses the hard 20-item ceiling that matters for a listing tool. What is missing is the meaning of the consent filter values and any hint about how result ordering interacts with paging, which leaves a small but real gap for a five-parameter search 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 description coverage is 0%, so the description carries the burden and mostly delivers: 'search' matches a name, an e-mail or a phone; buyers_only keeps only people with shop orders; sort is defined as 'recent' (newest first, default), 'top_spent' or 'last_order'. The consent enum (any/mailable/unsubscribed) is never explained and limit is only implied by the 20-per-call cap, so the compensation is strong but incomplete.

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?

Opening verb pair ('SEARCH or LIST') plus a precisely scoped resource ('people in the e-mail marketing base — the shop's customers, CSV imports, subscribers') tells an agent exactly what this returns and which data pool it draws from. The enumerated return fields and the sample user queries («покажи клієнтську базу», «хто купував найбільше») anchor the intent further, so it is clearly distinct from a summary or campaign tool.

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 routes counts elsewhere ('For how many there are in total call email_marketing_summary') and rules out export ('A full export is only in the cabinet's Email Marketing section'), which is real when-not guidance. It also explains the buyers_only and sort selectors in operative terms, but gives no explicit boundary against other people-lookup tools elsewhere in the catalog.

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