Agent Bounties

Prepare bounty for wallet review

prepare_bounty_post

DestructiveIdempotent

Use this when the person's AI has conversationally gathered complete bounty terms and received explicit approval. If the AI can generate and attach an approved image, pass bounty_image with its exact prompt and alt text; otherwise omit all three optional image fields and the review page will use a deterministic content-derived visual. Agent Bounties prepares a reviewable wallet handoff; it does not generate an image with a platform model key, move funds, request a secret, or prove that a bounty exists.

Input Schema

TableJSON Schema

Name	Required	Description
`goal`	Yes	Public digital outcome the solver must deliver.
`title`	Yes	Concise public bounty title.
`benchmark`	No	Optional exact public sandboxed_regression_v1 benchmark. Supply this and evidence_schema together. The source commit, benchmark digest, OCI image, command, and resource limits are immutable bounty terms.
`crowdfund`	No	Keep false to fund on creation. Set true only to deposit 0 USDC now.
`source_url`	No	Optional public HTTPS source issue or task URL.
`bounty_image`	No	Optional approved image generated in a compatible AI conversation. Agent Bounties stores this exact file; omit it and both image text fields to use the deterministic fallback visual.
`image_prompt`	No	Optional exact prompt used to generate a user-approved bounty image. Supply this, image_alt_text, and bounty_image together, or omit all three to use the deterministic fallback visual.
`image_alt_text`	No	Optional accessible description of the approved image. Supply this, image_prompt, and bounty_image together.
`evidence_schema`	No	Optional public submission-evidence schema paired with benchmark. Supply both verifier fields or neither.
`discovery_source`	No	Optional public attribution for how the poster found Agent Bounties.
`task_window_days`	No	Optional bounded work window in days; defaults to 30.
`solver_reward_usdc`	Yes	Solver reward in display USDC, for example 2.00.
`acceptance_criteria`	Yes	Binary or measurable public acceptance criteria.
`verifier_reward_usdc`	Yes	Verifier reward and refundable claim bond in display USDC, for example 0.10.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`goal`	Yes
`image`	Yes
`state`	Yes
`title`	Yes
`schema`	Yes
`post_url`	Yes
`crowdfund`	Yes
`source_url`	No
`next_action`	Yes
`target_usdc`	Yes
`bounty_created`	Yes
`task_window_days`	Yes
`evidence_boundary`	Yes
`solver_reward_usdc`	Yes
`acceptance_criteria`	Yes
`initial_funding_usdc`	Yes
`verifier_reward_usdc`	Yes
`wallet_signature_requested`	Yes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed2 schema fields changedSep 5, 2026

addedInput schema / properties / benchmark

{
  "description": "Optional exact public sandboxed_regression_v1 benchmark. Supply this and evidence_schema together. The source commit, benchmark digest, OCI image, command, and resource limits are immutable bounty terms.",
  "type": [
    "object",
    "null"
  ]
}

addedInput schema / properties / evidence_schema

{
  "description": "Optional public submission-evidence schema paired with benchmark. Supply both verifier fields or neither.",
  "type": [
    "object",
    "null"
  ]
}

First observedSep 5, 2026

TDQS

A4.3/5.0

Behavior4/5

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

The description discloses important boundary behavior beyond the annotations: it does not move funds, request a secret, generate an image with a platform model key, or prove existence. It does not explain the destructiveHint=true or openWorldHint=true traits, but the negative guarantees add decision-relevant context an agent would otherwise lack.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two dense sentences: the first carries the usage condition and image-field decision rule, the second states the safe boundaries. There is no filler or repetition of schema details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex tool with 14 parameters, nested objects, and an output schema, the description plus schema fully covers what the agent needs: preconditions, image-field coordination, fallback behavior, and explicit non-goals such as no fund movement or secret requests.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 14 parameters thoroughly. The description adds minor value by emphasizing the exact-prompt requirement and the deterministic fallback visual, but it does not materially extend the parameter semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific action ('prepares a reviewable wallet handoff') and names the exact resource ('bounty for wallet review'). The description also differentiates itself by listing what it does not do—generate an image, move funds, request a secret, or prove a bounty exists—so an agent can distinguish it from related prepare tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a crisp precondition: use only after complete bounty terms have been gathered conversationally and explicit approval is received. It also gives clear field-level guidance (pass all three image fields together or omit all three), though it does not explicitly name alternative sibling tools or state when-not-to-use in terms of alternatives.

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

All Agent Bounties tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0

Disambiguation3/5

Most tools are distinct by domain (comments, feeds, on-ramp, competitions), but prepare_bounty_action and prepare_bounty_post both trigger on an approved posting flow, and list_autonomous_bounties vs get_bounty_feed vs inspect_open_competition_v2 present overlapping read surfaces. The long 'use this when' guards help, but an agent could still select the wrong prepare or list tool.

Naming Consistency4/5

The names are almost uniformly snake_case verb_noun with predictable prefixes like prepare_, get_, and list_. Minor inconsistencies: add_bounty_comment vs list_bounty_comments (singular/plural), the v2 suffix, and compile_objective_with_cloud_agent breaks the concise verb_noun pattern.

Tool Count4/5

Thirteen tools is within the normal range for a platform covering bounty lifecycle, comments, feeds, competitions, and fiat on-ramp. However, the generic prepare_bounty_action plus separate prepare_bounty_post and several read/list variants make the set feel slightly heavier than the core domain needs.

Completeness4/5

The core bounty lifecycle (post, fund, solve/claim, complete, verify), status checks, listing, comments, and sharing are all represented. Missing explicit update/cancel or single-bounty detail operations are minor gaps because the prepare/status model and feed data cover most agent workflows.

Resources

Need Help?