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

The readOnlyHint=false annotation already tells the agent this mutates state; the description adds only that the operation happens in the hospital and is free. It does not disclose whether the shifts must net to zero (the example happens to sum to 0 but this is never stated), whether the operation is reversible or limited in frequency, or what the response contains. For a stat-mutating tool with a single weak annotation, that leaves the important behaviour undisclosed.

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?

A single dense sentence that front-loads the context (hospital, free) before the parameter example. Every clause carries information, though the inline example partially duplicates what the schema pattern already constrains.

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 one required parameter, no output schema, and only a readOnlyHint=false annotation, the description needs to explain preconditions, the zero-sum/valid-key rules, cost and limits. It conveys location and cost but omits the constraints that determine whether a call will succeed, leaving the agent under-equipped for a mutating operation.

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 0%, so the description must carry the parameter meaning, and it does partially: the sample value «str:81,dex:-9,int:-15,pow:-39,acc:-12,intel:-6» shows the comma-separated key:value syntax and implies signed deltas rather than absolute stats. It stops short of explaining that the numbers are delta shifts, that str/dex/int/pow/acc/intel are the only valid keys, or that the deltas must sum to zero — the format itself is already enforced by the regex, so the added value is mainly the worked example.

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?

The description identifies the feature ('Генетика в больнице') and the effect ('перенос параметров один в один' — a one-to-one redistribution of stats), which is more than a restatement of the name. However, it never states a concrete verb for what the call does (apply/perform the operation) and gives no differentiation from close siblings such as game_implant, game_hospital_cure, or game_implant_charge, so an agent must guess whether this is the genetics step or the cure step.

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?

The parenthetical 'бесплатная операция' and 'в больнице' hint at a location precondition and that it costs nothing, which is mildly useful. There is no explicit when-to-use versus alternatives (e.g. implant vs hospital cure), no stated prerequisites (level, being inside the hospital building), and no exclusions.

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