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

With only readOnlyHint provided, the description supplies meaningful extra context: marks are 'computed from numbers, not written by a language model' (determinism), the finished-report prerequisite, and that share_url is a read-only, no-sign-in link that exposes numbers and conclusions. That goes well beyond the safety annotation.

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 is front-loaded in the first clause, but the rest is a dense run-on paragraph mixing output-field documentation (items, wins, rows, best, better, mixed_markets) with share_url behavior. The content mostly earns its place given no output schema, but the presentation is 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?

With no output schema, the description carries the return-shape burden and does so credibly, documenting items/wins/rows/best/better and the mixed_markets ranking exception. Combined with the finished-report prerequisite and share_url semantics, an agent has what it needs to call it and interpret results.

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?

One parameter with 100% schema description coverage, so the schema already defines `ids` including 'as listed by list_research'. The description mostly mirrors 'two to five finished niche scans' and adds the finished-report requirement, but names no syntax or ordering detail beyond the schema. Baseline 3 applies.

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?

It states a specific verb and resource (puts niche scans side by side) plus scope (two to five) and the goal (choose between ideas). It never names a sibling like get_research or get_report, so an agent must infer the contrast itself, but the purpose is unambiguous.

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 rather than prescribed: it is for comparing ideas, and a prerequisite is stated ('Every scan needs a finished report'). It gives explicit when-to-give guidance for share_url ('only when they want to share'). It says nothing about when to prefer a single get_research/get_report over this comparison.

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