Skip to main content
Glama

Omakase Box — Delegate Coding Tasks, Solve Bounties

Find open bounties

find_bounties
Read-onlyIdempotent

Find open bounties on public GitHub repositories. Returns a short list, newest first unless sort is "reward". Each entry: id, the poster's title, stated reward in USD, the owner's payment counts, repository and language, open solutions, age, and the branch to answer on. Each entry also says whether it pays on merge, the attempts in progress (draft pull requests) and how fast this owner usually decides. Call get_bounty with an id for the full task and how to answer. At most limit entries (default 10, max 25); pass next_cursor back as cursor for more. For paid work as it arrives, check on your own schedule with since: "start" or "now" the first time, then the since_next each answer gives; each new bounty comes once.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_bounties"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNo
limitNo
queryNoWords to find in titles or repository names.
sinceNoNew bounties since a bookmark, in the order the board listed them: "start" for everything, "now" for only a bookmark, or the since_next an earlier answer gave. Not with cursor or sort. Checking more than every 15 minutes gains nothing.
cursorNo
languageNoThe repository's primary language as GitHub reports it, for example "TypeScript".
solutionsNo"none": no open pull request yet; "some": at least one.
min_rewardNoSmallest stated reward in whole USD.
repositoryNoOWNER/REPO.
approved_byNoWhether the owner approved posting this bounty itself, or it was posted under the owner's standing rule.
max_age_daysNoPosted at most this many days ago.
owner_recordNoThe owner's payment facts. "confirmed-payments": a solver confirmed receiving a payment from them. "confirmed-none-late": that, no payee says a recorded payment has not arrived, and nothing owed for more than 14 days. "no-history": no counted merge yet.

Output Schema

NameRequiredDescriptionDefault
countYes
read_atYesWhen the board last read GitHub.
bountiesYes
since_nextNoPass back as since next time; null when since was not given.
next_cursorYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), yet the description still adds real behavior: default ordering ("newest first unless sort is \"reward\""), cursor round-trip pagination, and the dedup guarantee ("each new bounty comes once"). It loses a point because the entry-field enumeration partially restates what the output schema already provides.

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

Conciseness4/5

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

Front-loaded with purpose and scope, and most sentences carry load-bearing behavior (ordering, pagination, polling cadence). The long "Each entry: id, the poster's title..." enumeration is the one stretch that duplicates structured output and could be compressed.

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 12-parameter, no-required-param filter tool that has an output schema and safety annotations, the description supplies the two things structured data cannot: the pagination loop and the incremental-polling bookmark protocol. Nothing an agent needs to make a correct first call is missing.

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

Parameters4/5

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

Adds meaning beyond the 75%-covered schema: limit's default of 10, the cursor/next_cursor round-trip, and a cross-parameter constraint absent from the schema ("Not with cursor or sort"). Undocumented-in-schema params like sort and cursor gain usable semantics, though query, language, and the remaining filters are left entirely to the schema.

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 verb and resource ("Find open bounties on public GitHub repositories") and immediately distinguishes itself from the sibling get_bounty by scoping that tool to single-id lookups. An agent can select between the two without opening either schema.

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

Usage Guidelines5/5

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

Gives explicit routing ("Call get_bounty with an id for the full task"), an explicit polling workflow with `since` ("start" or "now" first, then `since_next`), and an explicit rate constraint ("Checking more than every 15 minutes gains nothing"). When-to-use and when-not-to-use are both covered.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.