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

Annotations only declare idempotentHint and destructiveHint=false; the description adds that login is required, that access is read-only and limited to your own bounty, and crucially that PENDING does not mean paid. It also bounds behavior by excluding payer lookup and payment/refund execution. The read-only claim is consistent with the annotations.

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?

Four short clauses, front-loaded with the login/prerequisite and read-only scope, and no filler. The telegraphic semicolon-separated phrasing is dense but each clause (auth, scope, PENDING semantics, exclusions) earns its place.

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 single-parameter read tool with no output schema and only partial annotations, the description covers auth requirements, data scope, status interpretation, and explicit boundaries. The one remaining gap is what bountyId must contain, which neither schema nor description supplies.

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?

The schema documents bountyId not at all (0% coverage), so the description must carry the burden; it implies the ID belongs to the caller's own bounty (本人悬赏) but never defines the identifier's format or expected source. Meaning is added only indirectly through the ownership scoping.

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 states a specific verb (view/read) and resource scope: the caller's own bounty's persisted ledger and pricing. This distinguishes it from siblings like get_network_bounty or get_network_earnings, though it does not name the alternate sibling tools explicitly.

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 an explicit exclusion ('does not query payer or execute payment/refund, go to the App to continue yourself') and a semantic rule ('PENDING is not paid'), which tells the agent when not to rely on this tool and what a status value means. When to use it is only implied (checking your own bounty's persisted payment state), not stated outright.

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