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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so safety is covered. The description adds ordering (newest first) and that credits are included, which is useful context, but discloses nothing about result shape, counts, or limits.

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, but the middle line ("Every recorded answer earns its reward") is marketing filler that earns no place, and the genuinely useful pagination instruction is buried at the end with a wrong field name.

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, the description should clarify what a 'run' entry and 'credits' look like, which it does not. Pagination is at least mentioned, but the cursor-naming mismatch and absent return details leave gaps for a two-parameter listing 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 50% and the undocumented 'before' cursor is exactly the one the description should clarify. Instead the description refers to a 'next_before' cursor that does not match the schema's parameter name, creating confusion rather than adding meaning.

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 the resource ("Your runs, newest first, and the credits you earned"), but the name 'my_account' and title 'My rewards' suggest account/rewards info while the body describes a paginated run listing. It is unclear whether this is a run-history or account-detail tool, and no sibling (get_run, whoami) is named for disambiguation.

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?

The only usage hint is pagination ("For older runs pass the next_before you got as before"), but no guidance is given on when to use this versus get_run or whoami. The pagination reference also names a parameter ('next_before') that does not exist in the schema.

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