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

Annotations only declare readOnlyHint=true, so the description carries the rest and delivers real value: marks are computed from numbers rather than written by a language model, demand/CPC are never ranked across different markets (mixed_markets), and share_url is a no-sign-in link that exposes numbers and conclusions to anyone holding it.

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?

Purpose and prerequisite are front-loaded, and the dense output prose is justified because there is no output schema. It is nonetheless long and heavy for a single-parameter tool, with the rows/items/best/better enumeration bordering on verbose.

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?

With no output schema and only a readOnlyHint annotation, the description compensates fully: it explains the return structure (items, wins, rows, best, better), market-comparability rules, and the sharing semantics of share_url. An agent has everything needed to call and interpret it.

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 description coverage is 100% and there is a single param, so the schema already documents 'ids'. The description reinforces that scans must be finished but adds no format or syntax detail beyond the schema, making the baseline 3 appropriate.

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 a specific verb (compare) and resource (two to five finished niche scans) plus the goal (choosing between ideas). This clearly distinguishes it from siblings like get_research and list_research, which handle single scans or listings.

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 a clear use context ('help choose between ideas') and a hard prerequisite ('Every scan needs a finished report'), and constrains the range to two-to-five. It stops short of naming an explicit alternative tool for single-scan inspection, so it lands just below the top.

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