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

Annotations already declare readOnlyHint=true/destructiveHint=false, and the description reinforces 'nothing called here changes anything'. It adds context beyond the annotations: reads are free, execute bills the underlying tool, and the write half lives in a separate router. It does not, however, say what execute returns or how cost is metered, so it stops short of a 5.

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 the one-line contract and the free-vs-billed rule before the category inventory. The 18-tool category dump is long but functional for a router that must disclose what sits behind it. Slightly heavy, but little is wasted.

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 passthrough router with no output schema, the description covers routing, billing, account fan-out, the escape hatch to the write router, and the full tool inventory. The one gap is the return shape of execute, which an agent could reasonably want, though the tool's own schema is reachable via get_tool_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?

Schema coverage is 100%, so the baseline is 3, but the description goes further: it explains that action='execute' incurs the underlying tool's billing, that list_tools/get_tool_schema are free, that accounts is a read-fan-out capped at 20, and warns that tool_name must come from lookup rather than guessing. That is genuine meaning added on top of the schema text.

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 exactly what it is — reads plus tool lookup for TikTok Ads — and explicitly carves off the write half ('12 tools that change something run through tiktok_ads_write'). An agent can distinguish this router from tiktok_ads_write and the *_get_campaign_performance siblings without opening a 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?

Routing is fully specified: action=list_tools/get_tool_schema are free, 'never guess a tool_name', execute requires tool_name+arguments, accounts accepts a list or "all_active" capped at 20. It also names tiktok_get_campaign_performance as called by name rather than through the router, which is real alternative-selection guidance.

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