get_pending_actions

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds substantive behavior: the two action kinds, the 48-hour deadline risk, and that each item carries a follow-up tool name. It does not cover result shape, count, or pagination 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?

Two tightly written sentences: the capability and its two action kinds come first, then the urgency rationale. No filler, no repetition of the schema, and the actionable warning is front-loaded rather than buried.

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 does describe what comes back (settlements and decisions, each with the tool to call), which is the key thing an agent needs. Minor gaps remain around volume, ordering, and what an empty result means, but the core is 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?

Schema coverage is 100%, so address, agentId and maxJobs are fully documented in the schema. The description only gestures at "a wallet or identity", adding no format, defaults, or scoping detail beyond the schema, so the baseline 3 applies.

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 verb (List) and resource (pending actions on a wallet's/identity's bounties), and disambiguates the content into two named kinds (claim settlements, respond decisions). This clearly separates it from siblings like list_open_bounties and get_my_bounties, which list bounties rather than actionable items.

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?

"Check it regularly" plus the concrete consequence (missing a 48-hour window can lose a dispute by default) tells the agent when and why to invoke it. It also implies the next hop ("each with the tool to call"), but it does not explicitly name an alternative sibling or a when-not condition, so it falls short of a 5.

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