get_stats

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

No annotations exist, so description must convey all behavioral traits. It only describes output (aggregate stats) without mentioning read-only nature, side effects, or auth requirements.

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?

Single sentence with no waste, front-loading purpose and details.

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 zero-parameter, no-output-schema tool, description covers key output aspects. Could mention data freshness or caching, but overall complete.

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?

No parameters exist (0), so baseline is 4. Description adds meaningful context about output structure (by language, bug-fix-vs-feature), which suffices.

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?

Description clearly states the tool aggregates stats on the active bounty pool, specifying breakdowns by language and bug-fix-vs-feature, and total $. This distinguishes it from list_bounties (individual listing) and get_bounty (single bounty).

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 implied through the description of aggregated stats, but no explicit guidance on when to use vs. alternatives like list_bounties or find_matching is provided.

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