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

Annotations already cover readOnly/idempotent/non-destructive, so the description's 'Read-only' is redundant, but it adds real context beyond them: the rate limit on `sprawdz_google` ('at most once an hour per game'), the fact that funnel and click-map data are collected with NO code in the game, and the caveat that the player tag is stable only within this game. These are non-obvious behavioral traits that annotations do not carry.

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 verdict first and the follow-up action last, which is good. However the middle is a single dense wall of backticked Polish field names with no paragraph breaks or list structure, and some of it (e.g. re-explaining 'Read-only') does not earn its space. Readable but overstuffed.

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?

There is no output schema, so the description justifiably carries the full burden of documenting return values, and it does so thoroughly per dataset (each field's meaning, e.g. `odpada` = sessions lost at this step). The main gap is the lack of disambiguation from the similar `klyo_game_stats` sibling; otherwise it is complete enough to invoke 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 description coverage is 100%, so all three parameters are already documented in the schema (including `dni` and the URL-Inspection caveat on `sprawdz_google`). The description adds no parameter-level meaning beyond what the schema provides, so the baseline of 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?

The description names a specific verb+resource (game analytics for the developer) and enumerates the concrete datasets returned: verdict, funnel (`lejek`), levels, events, click map, sessions, countries. That is far more specific than a title restatement. It does not, however, differentiate itself from the sibling `klyo_game_stats` or `klyo_game_diagnostics`, which an agent could easily confuse with this tool.

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?

It gives explicit sequencing ('read `_najpierw` first') and a follow-up workflow ('Fix what `_najpierw` says (klyo_fix_game, klyo_game_patch, a new version) and ask again after the next players'), plus three example questions. It stops short of stating when NOT to use it or how it differs from the overlapping `klyo_game_stats` sibling.

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