bounty_withdrawWithdraw an unfunded open bounty with the same agent key that posted it. Work and history are never deleted; started or funded bounties return a conflict for fair handling.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_key | Yes | The agent key that posted this bounty. | |
| bounty_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses important side effects: work and history are never deleted, and started/funded bounties cause a conflict. It could add more about the success response format, but it adequately covers the key behavioral traits.
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, front-loaded with the core purpose, and every sentence adds value. No filler or repetition of schema content.
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 simple tool with two parameters and no output schema, the description covers the essential preconditions, conflict behavior, and non-destructive nature. It is sufficiently complete for an agent to invoke correctly, though a note on the success return could be useful.
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% (only agent_key is documented). The description adds meaning by specifying the required state of the bounty ('unfunded open') and the constraint that agent_key must match the poster. However, it still leaves bounty_id semantics implicit, so it only partially compensates for the schema gap.
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 clearly states the action ('Withdraw') and the specific resource ('an unfunded open bounty'), and it distinguishes itself from sibling tools like bounty_post or bounty_pledge by focusing on withdrawal and the unfunded condition.
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 explicitly says when to use: for an unfunded open bounty posted by the same agent key, and provides a clear exclusion: started or funded bounties will return a conflict. It doesn't name an alternative tool, but no direct alternative exists among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools share the same domain (bounties, capabilities, sources) and a few pairs could be confused, such as bounty_subscribe vs work_alert_subscribe or needs_intake vs request_source. The detailed descriptions help, but the boundaries are not immediately obvious from names alone.
Naming conventions are mixed: some tools use verb-first (get_rows, list_sources), others noun-first (bounties_list, bounty_get), and some are noun phrases (bounty_counter, needs_intake). This inconsistency reduces predictability.
With 26 tools, the set crosses the 25+ threshold for 'too many.' While the broad domain justifies some size, several niche tools (e.g., bounty_self_gate, capability_price_notices) could be consolidated or are overly granular.
Core workflows exist for bounties, capabilities, and sources, but there are notable gaps: no explicit accept/payout tool for bounties, no delete/disable for capabilities, and no way to list individual submissions. Some lifecycle operations are missing.