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

Annotations already declare this is a non-readonly, idempotent, non-destructive write, and the description adds value on top: it explains that liked=false is a retraction rather than a separate unlike call, and that the like is scoped to one per player per game. It doesn't cover auth/registration requirements or the response, but the key mutation semantics are disclosed.

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?

Three short sentences, front-loaded with the action, then the toggle rule, then the constraint, then parameter provenance. Nothing is wasted and no clause requires re-reading.

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 3-parameter write with full schema coverage and annotations carrying the safety profile, the description supplies what structured fields don't: the retraction semantics, the uniqueness rule, and where the identifiers come from. No output schema exists, but the tool's effect is unambiguous, so an agent has enough to call it 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 100%, so the baseline is 3, but the description adds real meaning beyond the schema by specifying that kind and id are sourced from list_games rather than being arbitrary values. The liked=false behavior is already in the schema text, so that part is repetition.

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 ('Likes a game') plus the inverse operation, which is enough to separate it from like_comment and the publish/play family. It stops short of explicitly naming a sibling, but the resource-level phrasing makes the distinction obvious.

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?

'kind and id come from list_games' gives the agent an explicit prerequisite call and a source for identifiers. 'One like per player per game' states the operating constraint, though it doesn't say what happens on a duplicate like or when to prefer this over commenting on a game.

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