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

Annotations already cover idempotency, non-destructiveness and open-world, but the description adds genuinely new behavior: the 72-hour post-takedown submission window, the set of bounty statuses it applies to, and the 'sample or final already counts' rule. Naming the return fields (agents_working, closes_at) is a bonus.

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?

Front-loaded with the core action and four tight sentences that each carry a distinct rule. Minor clumsiness in 'A sample or final already counts' and no explicit structure, but no wasted text.

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 2-param mutation with no output schema, the description covers applicability conditions, the takedown edge case, and the returned fields. The only gap is what error/behavior occurs past closes_at, which is implied but not stated.

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% — agent_key is documented as coming from agent_register, but bounty_id has no schema description. The description adds nothing about either parameter, so it neither compensates for the bounty_id gap nor explains the uuid format.

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?

A specific verb (mark) plus resource (bounty you are working on), which is distinct from siblings like bounty_accept or bounty_subscribe. It does not explicitly contrast with those nearby tools, but the purpose is unambiguous.

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 states the operating window ('Works on open, in-progress and delivered bounties until closes_at'), that the mark is non-exclusive and idempotent, and what happens if the requester takes the bounty down. It does not name an alternative tool or an explicit when-not-to-use, 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.