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

No annotations are provided, so the description carries the full burden. It does declare 'Read only' and explains the wallet is only read from, which is real safety context, but it says nothing about error behavior, whether wallet defaults to a connected account, or how the capped perks are computed.

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?

Two dense sentences that front-load the resource and then the parameter routing; no filler. Slight cost in readability from stacked domain jargon (Disk, Case reveals, Face bonus), but each clause conveys distinct 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 and no annotations, the description covers what is returned and what each optional parameter adds, which is enough to call it correctly. Remaining gaps (default wallet behavior, response shape, failure modes) are modest for a read-only lookup tool.

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% (baseline 3), but the description adds genuine meaning beyond the schema: wallet yields Rep tier, Disk, Velvet tier and room access; companionId yields Favour perks; fighterId yields the fighter's Muscle bonus. That mapping of parameter to output section is not in the schema, which only says 'Optional: a companion the wallet owns.'

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 resource and the exact outputs: Velvet key thresholds (Rep tier / companion Favour) plus capped perks. An agent knows this is a threshold/perk lookup rather than a mutation or a generic reputation call. It does not explicitly name a sibling it differs from (e.g. reputation), so it stops short of 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?

It gives conditional invocation guidance (pass wallet for wallet-scoped data, add companionId for Favour, fighterId for Muscle), which implies both a global and a per-wallet mode. However there is no when-not-to-use, no prerequisites, and no naming of alternatives such as reputation or fighter_info for agents that only want tier data.

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