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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, yet the description adds real operational context: 60 requests/min limit, no authorization required, and the failure contract ('Невідомий slug → відповідь-помилка з підказкою, а не порожній результат'). It also disambiguates null semantics for rating, tariffs, and first_loan_zero_percent, which annotations cannot convey.

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 opening is good, but the rest is a single massive run-on paragraph with nested parenthetical clauses defining each returned field. Much of the field-by-field explanation belongs in a response schema rather than the tool description, and the density makes it hard to scan.

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?

There is no output schema, so the description must carry the return-value burden — and it does, enumerating conditions, tariffs, first-loan promo fields, borrower requirements, legal entity, NBU license, document links, rating and update date. Error behavior, rate limit, and attribution (mfoxa.com.ua / canonical_url) round it out.

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 100%, so the schema documents slug format and the lang enum (uk/ru) on its own, setting a baseline of 3. The description earns an extra point by stating where slug comes from (list_mfo / URL /mfo/{slug}) and by clarifying that lang changes names/text only, not the dataset — a semantic detail the schema enum alone does not express.

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+resource+key: 'Повна картка однієї МФО за slug' — full record for one MFO fetched by slug. It enumerates the exact content returned (tariffs, first-loan promo, requirements, licenses, rating) and explicitly names the siblings it is not (get_reviews for text reviews, search_offers/get_category for comparison).

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 precondition ('Використовуйте, коли компанія вже відома') and tells the agent where to obtain the required slug ('slug беріть із list_mfo або search_offers'). It routes alternatives explicitly: get_reviews for reviews, search_offers or get_category for multi-MFO comparison.

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