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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description discloses the rate limit (60 запитів/хв), auth-free access, error behavior for unknown slugs (відповідь-помилка з підказкою), the data source (каталог МФОХА), and an attribution requirement (посилайтеся на canonical_url). This significantly enriches the safety and failure-mode picture beyond what structured annotations provide.

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 description is dense but every clause earns its place: purpose and response contents, usage trigger with examples, alternative routing, then behavioral notes (auth, rate limit, error, attribution). It is front-loaded with the core definition and flows logically from what → when → alternatives → behavior, with zero filler.

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?

Despite having no output schema, the description enumerates the key response fields (criterion, sort order, MFO conditions table, canonical_url, markdown_url), covers error behavior, rate limits, and auth, and routes sibling usage. For a simple read-only fetch by slug, nothing an agent needs to call it correctly is missing.

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 baseline is 3; both lang and slug are already documented in the schema, including the language-versus-data distinction and slug examples. The description adds one genuinely new operational pointer — «slug беріть із list_categories» — telling the agent where to source valid slugs, which nudges it above baseline.

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 verb and resource — «Одна тематична добірка за slug» — and enumerates the response contents (критерій відбору, порядок сортування, таблиця МФО з умовами, canonical_url, markdown_url). It explicitly names sibling tools it is not, so an agent can distinguish get_category from search_offers, get_mfo, and list_categories without opening their schemas.

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?

Explicit when-to-use guidance is given: «Використовуйте, коли запит збігається з готовою редакційною добіркою», with concrete query examples («кредит на картку», «позика без відмови»). It also states routing exclusions with alternatives: search_offers for numeric matching, get_mfo for single-MFO details, list_categories for the full list of selections — nothing is left to inference.

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