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

Annotations already declare readOnlyHint and openWorldHint, so the description rightly spends its words elsewhere: result ordering, the strict inequality on `since`, and the presence of a next_since cursor in the response. It doesn't mention rate limits or behavior when since is in the future, but the disclosed traits are the ones that matter for a polling feed.

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 sentences, no filler, and the core semantics appear before the polling convention. Everything present 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?

With no output schema, the description supplies the one piece of return-value knowledge an agent needs (next_since) and otherwise relies on a fully documented schema. Nothing required to call it correctly is missing.

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 the schema already documents all seven parameters; the description adds value beyond it by clarifying that `since` is strictly exclusive and that a returned next_since is meant for the next `since` value. That roundtrip contract is not expressed in the schema.

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 (bounties), a precise temporal filter (first seen strictly after `since`), and an ordering (newest first). It does not name a sibling to contrast with, so an agent must infer how it differs from list_bounties and get_bounty, but the delta/feed semantics are clear enough.

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 second sentence gives explicit operational guidance: capture `next_since` and pass it on the next call to get only new items, which describes the intended polling workflow. It stops short of stating when to prefer this over list_bounties.

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