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

Annotations only declare it as a safe, idempotent read; the description supplies the real caveats: heat weights are an uncalibrated estimate, revenue figures are ranged estimates and never measured sales, and computed niches return null for stage/heat/window/studios. Grade semantics (A/B/C/D data-point completeness) give the agent a way to judge reliability before acting.

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?

It is front-loaded with the mode distinction, but the body is one long comma-chained sentence that enumerates output fields and buries the grade and revenue caveats mid-stream. Much of the field enumeration duplicates the output schema.

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?

Because an output schema exists, the field-by-field enumeration is largely redundant, while the genuine gaps (when to pick this over compare_games or find_opportunities, and whether platform omission changes the mode) remain unaddressed. It is nonetheless complete enough on methodology and data reliability to call the tool correctly.

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 already 100%, so the baseline is 3; the description earns more by explaining that a niche can be a ranked label, a genre, or a raw keyword, and that crossPlatform maps the same mechanic between Roblox and Fortnite. It adds resolution semantics the schema's examples do not fully convey.

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 and resource ('Evaluate one niche') and immediately explains the two modes a niche can be resolved into ('tracked' vs 'computed'). It never names a sibling, so an agent comparing it against get_gap_analysis or find_opportunities must infer the split itself.

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 ('always in the same format') and the niche parameter is described as coming 'from list_niches', which gives a weak ordering hint. There is no explicit when-to-use-this vs when-to-use-a-sibling guidance, no prerequisites, and no exclusions.

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