yandex_setup_toolsets

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

Annotations mark it non-read-only, non-destructive, and non-idempotent, so the safety profile is partly carried there. The description adds the key side-effect detail the annotations don't: write=true persists to mcp.local.json (stdio), plus the 'No secrets' assurance and the output shape (YANDEX_TOOLSETS + token cost). It is not strictly destructive, which is consistent with destructiveHint=false.

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?

Highly compact with arrow notation and no filler; the output consequence is front-loaded after the input choices. The terseness is efficient but borders on shorthand, which slightly reduces readability without being wasteful.

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?

An output schema exists, so return values need not be detailed, and the config-file write behavior is covered. However, gaps remain for a 4-parameter setup tool: default behavior when nothing is passed, precedence between platforms and preset, and any preconditions are unstated. Adequate but with clear omissions.

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 0%, so the description must supply parameter meaning and it largely does: it enumerates platform values (direct, metrika, webmaster, audience, wordstat, serp, maps, manage), preset values (direct-only, analytics, seo, everything), tool_loading modes (eager|lazy), and write=true semantics. It does not explain the defaults or whether platforms and preset are mutually exclusive, leaving a small gap.

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 states a specific action and resource: pick Yandex platforms or a preset plus tool_loading mode, producing YANDEX_TOOLSETS and a token cost. It singles itself out from the sibling platform tools, which are the tools being selected rather than the selector. The telegraphic 'Pick ... ->' phrasing is clear but not fully fleshed out as a sentence, so it lands just below a 5.

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?

Usage is implied — this is a setup/configuration tool to be run when choosing which toolsets to load — but the description never says when to call it (e.g. before using platform tools) or how platforms and preset interact if both are supplied. No explicit when-not or alternative is given. Only implied context, so a 3.

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