The issue tracker AI coding agents pull work from: atomic claims, dependency-aware dispatch.
Scored across 1 tool
There is only one tool, so there is no ambiguity or risk of an agent misselecting between overlapping tools. Its single-purpose role as a setup/bootstrap operation is clearly communicated.
The name `setup_status` follows a clean verb_noun snake_case pattern and clearly describes its purpose. With only one tool, there are no conflicting or inconsistent naming conventions.
One tool is intentionally appropriate for the bootstrap-only state, since the server is not set up yet and all other tools will load later. It is slightly thin as a full server surface, but reasonable for the current stage.
For the setup-phase workflow, `setup_status` covers the complete process: running the CLI, surfacing the approval URL, acting on the result, and asking the user to restart. There are no obvious missing steps within the documented bootstrap flow.
Retasc is not set up in this folder yet, so this is the only tool available and the only one that will work. Call it and follow what it returns. In short: YOU run npx @retasc/cli@latest bind --json in this folder, in the background, having first told your human that a browser is about to open. Post the approve URL it prints to them as a link, act on what it reports back, and when it finishes ask them to restart you so the rest of the tools load. The click and the restart are theirs; everything else is yours.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The schema and annotations are empty, so the description carries the full burden of disclosing behavior. It does this exceptionally well: it tells the agent to run the CLI in the background, warns that a browser will open, states that an approve URL will be printed and must be posted as a link, and explains the handoff/restart responsibility. Safety/operational details, such as which actions belong to the human vs. the agent, are also explicit.
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?
The description is dense and action-rich with clear sequencing, and it front-loads the key context (setup not yet done, only tool that works). It loses one point because 'Call it and follow what it returns' is redundant with later sentences ('act on what it reports back'), and 'In short' introduces a detailed explanation that actually starts a rather large summary, which causes in structure. Otherwise every clause earns its place.
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 zero-parameter tool with no output schema/siblings, the description is remarkably complete. It gives the exact shell command, the background running behavior, the human-notification step, the approval-link workflow, what to do with reports, and the restart handoff. An agent is able to execute the whole flow correctly without any additional context.
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 input schema has zero parameters, so there are no parameter semantics for the description to add. With a 0-parameter tool, the baseline is 4, and the description fully covers the only 'inputs' that matter: the exact CLI command to run and the operational steps to take. Nothing about parameters is missing.
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 identifies the tool as the sole action available when Retasc is not yet set up, and states exactly what a successful call accomplishes (running the bind CLI, producing an approval URL, and completing setup). It is not a tautology; it gives a specific verb and resource (setup via `npx @retasc/cli@latest bind`). Even with no siblings, any agent reading it will understand why this tool exists and when it applies.
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 states the triggering condition: 'Retasc is not set up in this folder yet, so this is the only tool available and the only one that will work.' This tells the agent exactly when to invoke it. Since there are no sibling tools, the description doesn't need to name alternatives; it still gives unambiguous context and even explains that after restart the rest of the tools load.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
accept_inviteadd_relationbilling_summarycheck_claimcheckpointclaim_ghostclaim_issuedismiss_ghost_promptget_attachmentget_attachment_fileget_issueget_projectheartbeatimport_historylatest_importlist_attachmentslist_claimable_ghostslist_commentslist_connectorslist_import_sourceslist_import_statuseslist_import_targetslist_issueslist_labelslist_memberslist_projectslist_review_candidatesmint_session_keynext_batchnext_issueobsolete_attachmentprepare_attachment_uploadqueue_statusreactivate_memberrelease_issueremove_relationretire_memberretract_commentrevoke_connectorrun_importsave_attachmentsave_attachment_filesave_commentsave_issuesave_labelsuspend_memberusage_summarywhoamiclaim_ghostdismiss_ghost_promptlist_claimable_ghostsimport_historylatest_importlist_import_sourceslist_import_statuseslist_import_targetslist_review_candidatesrun_importsetup_statusaccept_inviteget_attachment_filesave_attachment_fileclaim_issue1 field changedInput schema / properties / claimTokenAdded value: +{
+ "description": "ONLY to resume your own claim after a restart: the claim_token from before, which moves that live lease onto this session. Omit when claiming new work. It proves you are the same agent continuing — a session that never held the issue doesn't have it, and it can never move a claim to a different agent.",
+ "type": "string"
+}save_issue2 fields changedInput schema / properties / assignee / descriptionPrevious value: -"Responsible human (routing lane, distinct from claiming): a human member name, 'me', or '' to unassign. Optional for most statuses — unassigned issues stay in the global pull pool — but REQUIRED whenever the write leaves the issue in `review` (RTSC-347 + RTSC-400), including a CREATE with `status:\"review\"` (which records YOU as the submitter, so the assignee must be a different active principal). While an issue sits in `review`, '' does NOT unassign: clearing it, or naming the submitter's own principal or a suspended/retired member, is rejected even on a write that never mentions `status`. Send it back with `status:\"todo\"` first if you want it unassigned."New value: +"Responsible human (routing lane, distinct from claiming): a human member name, 'me', or '' to unassign. Optional for most statuses — unassigned issues stay in the global pull pool — but REQUIRED whenever the write leaves the issue in `review` (RTSC-347 + RTSC-400), including a CREATE with `status:\"review\"` (which records YOU as the submitter, so the assignee must be a different active principal). While an issue sits in `review`, '' does NOT unassign: clearing it, or naming the submitter's own principal, a suspended/retired member, or a placeholder nobody has signed in as (left by an import or a restore), is rejected even on a write that never mentions `status`. Send it back with `status:\"todo\"` first if you want it unassigned."Input schema / properties / status / descriptionPrevious value: -"`review` (RTSC-257) = work finished, pending human acceptance: it still BLOCKS dependents (unlike done) and releases your lease so a reviewer can claim it. `assignee` is REQUIRED on every write that LEAVES the issue in `review` (RTSC-347 + RTSC-400) — name the reviewer's human lane, an ACTIVE member who is a DIFFERENT principal than whoever submitted it (author ≠ reviewer). It is a property of the STATE, not of the transition: it applies when you move an issue to review, when you CREATE one with `status:\"review\"`, and to any later write that changes a live review's assignee — including a write that names no `status` at all. So `assignee:\"\"` can't clear a live review's reviewer, and it can't be re-pointed at the submitter or at a suspended/retired member: a review parked on a lane nobody can claim strands, non-terminal, blocking its dependents. To unassign, send it back first (`status:\"todo\"`). The reviewer's agent then promotes it (`status:done`, unblocks dependents) or sends it back (`status:todo` + a comment). Whether to use review is your team's convention; that it must be assigned is not."New value: +"`review` (RTSC-257) = work finished, pending human acceptance: it still BLOCKS dependents (unlike done) and releases your lease so a reviewer can claim it. `assignee` is REQUIRED on every write that LEAVES the issue in `review` (RTSC-347 + RTSC-400) — name the reviewer's human lane, an ACTIVE member who is a DIFFERENT principal than whoever submitted it (author ≠ reviewer). It is a property of the STATE, not of the transition: it applies when you move an issue to review, when you CREATE one with `status:\"review\"`, and to any later write that changes a live review's assignee — including a write that names no `status` at all. So `assignee:\"\"` can't clear a live review's reviewer, and it can't be re-pointed at the submitter, at a suspended/retired member, or at a member nobody has ever signed in as (an unclaimed placeholder left behind by an import or a restore — RTSC-408): a review parked on a lane nobody can claim strands, non-terminal, blocking its dependents. To unassign, send it back first (`status:\"todo\"`). The reviewer's agent then promotes it (`status:done`, unblocks dependents) or sends it back (`status:todo` + a comment). Whether to use review is your team's convention; that it must be assigned is not."save_issue2 fields changedInput schema / properties / assignee / descriptionPrevious value: -"Responsible human (routing lane, distinct from claiming): a human member name, 'me', or '' to unassign. Optional for most statuses — unassigned issues stay in the global pull pool — but REQUIRED when `status:\"review\"` (RTSC-347): a review must name a different-principal reviewer or it's rejected."New value: +"Responsible human (routing lane, distinct from claiming): a human member name, 'me', or '' to unassign. Optional for most statuses — unassigned issues stay in the global pull pool — but REQUIRED whenever the write leaves the issue in `review` (RTSC-347 + RTSC-400), including a CREATE with `status:\"review\"` (which records YOU as the submitter, so the assignee must be a different active principal). While an issue sits in `review`, '' does NOT unassign: clearing it, or naming the submitter's own principal or a suspended/retired member, is rejected even on a write that never mentions `status`. Send it back with `status:\"todo\"` first if you want it unassigned."Input schema / properties / status / descriptionPrevious value: -"`review` (RTSC-257) = work finished, pending human acceptance: it still BLOCKS dependents (unlike done) and releases your lease so a reviewer can claim it. `assignee` is REQUIRED when moving to `review` (RTSC-347) — name the reviewer's human lane, an ACTIVE member who is a DIFFERENT principal than whoever submitted it (author ≠ reviewer). A review with no assignee, or one assigned to a suspended/retired member, is rejected: such a review is invisible to every lane AND locks the submitter out (they can't claim their own review back), so the work would strand. The reviewer's agent then promotes it (`status:done`, unblocks dependents) or sends it back (`status:todo` + a comment). Whether to use review is your team's convention; that it must be assigned is not."New value: +"`review` (RTSC-257) = work finished, pending human acceptance: it still BLOCKS dependents (unlike done) and releases your lease so a reviewer can claim it. `assignee` is REQUIRED on every write that LEAVES the issue in `review` (RTSC-347 + RTSC-400) — name the reviewer's human lane, an ACTIVE member who is a DIFFERENT principal than whoever submitted it (author ≠ reviewer). It is a property of the STATE, not of the transition: it applies when you move an issue to review, when you CREATE one with `status:\"review\"`, and to any later write that changes a live review's assignee — including a write that names no `status` at all. So `assignee:\"\"` can't clear a live review's reviewer, and it can't be re-pointed at the submitter or at a suspended/retired member: a review parked on a lane nobody can claim strands, non-terminal, blocking its dependents. To unassign, send it back first (`status:\"todo\"`). The reviewer's agent then promotes it (`status:done`, unblocks dependents) or sends it back (`status:todo` + a comment). Whether to use review is your team's convention; that it must be assigned is not."prepare_attachment_uploadCoding agents from Claude Code, Cursor and Codex claim jobs and lock files on one shared board.
Task tracking built for coding agents. Work is leased, so two agents never take the same SubTask.
Task management for teams building with AI agents. Agents claim tasks and report progress.
AI work orchestration for plans, tasks, teams, and coding-agent dispatch.
Add one secure layer between your agents and this server.
