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

Annotations already declare readOnly/idempotent/non-destructive, yet the description still adds substantial non-obvious behavior: a default floor hiding small Steam games (50+ reviews in 7 days and 50+ players online), the exclusion of games with unknown positive share in minPositivePct results, and source/asOf stamps on every record. It stops short of describing pagination limits beyond nextCursor or result ordering ties, so it is strong but not exhaustive.

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 platform caveats are front-loaded, and most sentences carry operational detail rather than filler. The grade definition is dense and nested inside parentheses ("grade = completeness of the game record (A = 8+ of 10 data points known, B = 6-7, C = 4-5, D = fewer)"), which is harder to parse than a short pointer would be, but no sentence is truly 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 14-parameter filtered-list tool with an output schema and full read-only annotations, the description covers what annotations and schema cannot: cross-tool routing, default hiding behavior, definitional resources, and the estimate-grade caveat on revenue figures. Nothing an agent needs to call it correctly or interpret results is missing.

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 adds real meaning beyond the schema: sort values denote the field sorted by, momentum is the default, newest means smallest ageDays, and it explains why includeSmall exists by describing the hidden floor. The grade/estimate caveat clarifies how to read returned figures rather than adding new filter semantics.

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?

Opens with a specific verb and resource plus scope: "Find games that are gaining players or reviews right now," then immediately names the covered platforms and the ones lacking momentum data. It explicitly positions itself relative to siblings ("Start here for what is rising questions, then call get_game on an id"), so an agent can choose it without inspecting another 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?

Gives explicit when-to-use guidance ("Start here for what is rising questions") and the follow-up step (get_game on an id), plus a pointer to list_niches for nicheStage values and the wieldr://methodology resource for definitions. It also names the condition that changes behavior (includeSmall for hidden small Steam games), which is the key usage decision an agent must make.

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