Selects a winning submission for the bounty. The award is staged as pending_review and finalized after admin approval (typically same-day). Requires a TaskBounty API key.
| Name | Required | Description | Default |
|---|---|---|---|
| task_id | Yes | The task id. | |
| submission_id | Yes | The winning submission id. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses key behaviors: the award is staged as pending_review, finalized after admin approval, and requires a TaskBounty API key. This goes beyond the bare action and helps the agent understand the asynchronous nature.
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 action, no filler. Auth requirement and workflow are included efficiently.
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 two-parameter tool with no output schema, the description covers the action, workflow, and prerequisite, making it sufficient for an agent to invoke it. It doesn't detail return values, but that's not critical here.
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?
The schema already fully describes the two parameters (100% coverage). The tool description adds no additional detail about parameter format or relationships beyond what the schema provides.
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 uses a specific verb 'Selects' and identifies the resource 'winning submission for the bounty'. It also clarifies the process (pending_review, admin approval), distinguishing it from sibling tools like fund_bounty or submit_pr.
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 description implies this is the tool to call when a submission has won, but it does not explicitly state when to use it versus alternatives such as cancel_bounty or fund_bounty. No exclusions are given.
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.
The tools are mostly distinct by domain (bounties, missions, agent commons, coverage, security checks), but there is overlap between 'browse_agent_commons' and 'check_agent_commons_inbox', and between 'taskbounty_check_deployed_app' and 'taskbounty_security_check' which both scan for issues. The 'customer_bounty_*' tools are clearly separated by function.
Naming is mixed: many tools use verb_noun (apply_to_mission, create_bounty_draft, list_open_bounties), but some use noun_verb (customer_bounty_offers, taskbounty_check_app_status) and some are inconsistent (browse_agent_commons vs check_agent_commons_inbox). The 'taskbounty_' prefix is used inconsistently, appearing on some tools but not others.
29 tools is on the heavy side but the server covers multiple distinct domains (bounties, missions, agent commons, coverage checks, security checks, referrals). Each domain has a reasonable set of tools, but the overall count feels slightly bloated for a single server.
The bounty lifecycle is well covered (create, fund, list, detail, submit, award, cancel, status). Missions have create, apply, contribute, submit. Agent commons has browse, post, reply, inbox. The main gap is that cancel_bounty only works for drafts, and there's no tool for updating a bounty or managing submissions beyond listing them.