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

Annotations already declare readOnly, idempotent, and closed-world, so the safety profile is covered. The description adds genuine behavioral value by disclosing the three computed outputs (wager remaining, cheapest-game cost, sports bet equivalent), telling the agent what kind of answer to expect. It stops short of describing assumptions behind 'cheapest games' or the cost model.

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 with no filler; every clause contributes a distinct output. It is slightly awkward to parse because the input modes and outputs are crammed together, but nothing is 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?

With an output schema and full annotation coverage, the description only needs to convey the computation model, which it does. The remaining ambiguity — whether level is needed alongside totalWager and what currency/units the cost uses — is minor but not resolved in the text.

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. The description goes beyond the schema by clarifying the two mutually exclusive input modes: either level plus progress percentage, or a total wagered figure ('instead of level and progress'), which is semantically important given zero required parameters.

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 computed resource — wager remaining to the next Stake VIP level — plus the derived outputs (cost on cheapest games, sports bet equivalent). No sibling tool covers VIP progress, so disambiguation is implicit rather than stated. It lacks an explicit verb ('calculates'), reading as a noun phrase, which keeps it just short of a 5.

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?

Usage is only implied: an agent can infer this is the tool for VIP-level questions, but the description never says when to prefer it or what to do when no level data is known. No alternative sibling is named or excluded, though the sibling list offers no obvious overlap.

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