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

Goes well beyond the readOnly/non-destructive annotations by disclosing persistence behavior ('needs no squad and saves nothing'), determinism ('the same list always gives the same teams'), and full return shapes (bibs/nonBibs with average ratings, team list, verdict, group-chat message). This is exactly the context annotations cannot 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?

Front-loaded with the core purpose, then constraints, alternatives, and return values in a tight sequence. Dense and slightly long for a single paragraph, but nearly every clause carries actionable information.

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 no output schema present, the description fully compensates by describing both return variants and the verdict/message fields, plus the input constraints and no-persistence guarantee. An agent has everything needed 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: player-count constraints per team mode (4-30 for two, 6-30 for three), keeper spreading, and the shuffle parameter's effect on producing a different fair split. Only the teams-mode third-team use case ('winner-stays-on') is extra flavor rather than parameter detail.

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 — split football players into fair, balanced teams — and immediately names the sibling it is not (pick_teams) for squad-owned games. An agent can distinguish it from make_fixtures, reshuffle_teams, and pick_teams without opening a 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?

Explicit about when to use it (standalone group of 4-30 or 6-30 players, no squad needed, nothing saved) and when not to ('for a Squadcard squad's own game, use pick_teams instead'). It also explains the alternative split route via the shuffle parameter.

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