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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the rest and does well: default result size, hard cap of 10, the availability filtering model (stock-and-order when the field is absent, all means no quantity cut), a named error mode (sort-invalid), and a response field (table) plus hidden_message to relay to the human. The remaining gap is that it never says what the ranking does with ties or how many candidates are scanned, but the operational surface is otherwise well disclosed — and it correctly warns 'заказ не обещай', which matches readOnly semantics.

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 purpose then a chain of conditional rules; each sentence carries an operational constraint, and nothing is decorative. The telegraphic dash-style makes it dense to parse but it is appropriately sized for a multi-behaviour tool with eight parameters.

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?

For a complex nested-schema tool with no output schema, the description covers the selection semantics, defaults, the error path, and how to present and relay the result (table field mirrors the site, hidden_message goes to the person). An agent has enough to call it and handle the response without guessing.

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 75%, so the schema already documents sort, availability, thresholds and most catalog fields; the description largely restates the limit default (5) and cap (10) and the target_flux→flux-distance-asc rule that the sort schema already states. It does add operational meaning to availability (absent field = stock-and-order, min 1; 'при названной маркировке наличие не проверяется'), but says nothing about price, temperature, or the catalog.min_quantity vs availability.min_quantity split, which is the most confusing part of the schema.

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?

Opens with a specific verb and resource (расчётный подбор светодиодов) plus the three dimensions of the match (корпус, CCT, рабочий ток), and immediately names the sibling it is not: led_catalog_search is a 'прайс без расчёта'. An agent can distinguish the two without opening either schema.

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?

Gives an explicit routing rule for the missing-required-input case: no current → call led_catalog_search or ask the user for the current. It also states the escalation path for limit ('просят больше, вызывай с limit 10') and when sort is refused (sort-invalid Without target_flux). Alternatives and preconditions are spelled out rather than implied.

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