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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real context beyond that: the score is computed from catalog signals (price per resource, entry price, trust, terms, tech, reach) and the response includes plans count and entry price. It doesn't discuss pagination or whether hosts outside the top N are omitted.

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?

One dense, front-loaded sentence that leads with what the tool returns and then moves to the category switch. The long parenthetical category list is information-dense rather than wasteful, though the sentence is packed enough to be slightly 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?

For a read-only three-parameter ranking tool with no output schema, the definition says what is scored, how, what fields come back, and how category and empty-string behave. The only gap, the limit maximum, is already enforced in the schema.

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?

With 33% schema coverage, only locale is documented in the schema. The description carries the category semantics very well, spelling out ambiguous values ('abroad (ru only)', 'crypto (not on ru)', 'vpn (corporate VPN)') but says nothing about locale or the limit cap of 25. It compensates for the hardest parameter but leaves two of three thin.

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?

States precisely what is returned: a ranked top list of VPS hosts from the accsly.io rating, with a 0-10 score, plans count and entry price. It implicitly separates itself from search_vps/get_vps_host by being a ranked-by-score list, but never names those siblings. The purpose is clear and specific even without explicit sibling routing.

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?

Explains the category narrowing and that an empty category yields the overall rating, which is genuine usage guidance for the main selection decision. However, it gives no direction on when to prefer this over search_vps or compare_hosts, so the agent must infer the boundary from the ranking framing alone.

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