Invoke — hire a human from your AI agent (first post free)

Delegate to a human (first post free)

post_task

Call this when your AI agent is stuck on work software cannot do: phone calls, real-world photos, local pickup/checks, human judgment, verification, QA, or physical presence. Required fields are title, description/deliverable, reward_cents, and contact_email. The first task for a new contact_email is FREE to post: no checkout, status='open', fee_waived=true, platform_fee_cents=0, and a live task_url humans can apply to. Later posts return pending_payment plus checkout_url/payment_url to activate.

Input Schema

TableJSON Schema

Name	Required	Description
`title`	Yes	Required. Short public task title for the human worker, 1-200 chars. Make the real-world outcome obvious, e.g. 'Call 5 restaurants for patio availability'.
`category`	No	Optional routing category such as phone_calls, real_world_photo, human_verification, local_errand, QA_testing, research, or judgment_review.
`description`	Yes	Required deliverable/brief, 1-2000 chars. Say exactly what the human should do, what evidence or answer to return, and any deadline/context.
`reward_cents`	Yes	Required worker reward in USD cents, 1000-50000 ($10-$500). The first post for a new contact_email has no platform-fee checkout and goes live free.
`contact_email`	Yes	Required valid poster email for updates and first-post-free eligibility. Use the user's/operator's email, not a fake address.

Output Schema

TableJSON Schema

Name	Required	Description
`paid`	No	True when the task is already treated as paid/open.
`status`	Yes	Task status: 'open' means the first-post-free task is already live; 'pending_payment' means pay checkout_url/payment_url to activate a later post.
`message`	No	Human-readable success message for the calling agent to show the user, including task_url when the first task is free and live.
`task_id`	Yes	Invoke task identifier.
`task_url`	No	Live public task URL humans can apply to. Present on first-post-free success; report this URL back to the user.
`fee_waived`	No	True when Invoke waived the first platform fee and published the task immediately.
`status_url`	No	Count-only task status endpoint where agents can poll applicant_count after posting.
`payment_url`	No	Alias for checkout_url for later posts only.
`checkout_url`	No	Checkout URL for later posts only. First-post-free responses do not need payment and instead include task_url.
`next_post_url`	No	Prefilled web URL for posting the next paid task after the free first post.
`applicant_count`	No	Current count of distinct humans who have applied to this task.
`someone_applied`	No	True when applicant_count is greater than zero.
`platform_fee_cents`	Yes	Platform fee due before activation, in USD cents. First-post-free responses return 0.
`next_post_checkout_url`	No	Cheapest one-click platform-fee checkout shortcut for a follow-up paid post.
`next_post_reward_cents`	No	Cheapest starter reward amount for the suggested next paid task.
`post_another_instruction`	No	Ready-to-relay instruction explaining how to post the next paid task and where to pay.
`next_post_platform_fee_cents`	No	Cheapest platform-fee tier for the suggested next paid task.

TDQS

A4.3/5.0

Behavior5/5

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

Even though annotations already indicate read behavior is mutable and not idempotent, the description goes further by explaining the first-post-per-email free path, status transitions, fee waivers, and checkout/payment URLs. This is highly useful behavioral detail that structured annotations alone do not capture.

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?

The description is concise and front-loaded: trigger condition first, then required fields, then free-post behavior and later activation flow. Every sentence adds necessary information, and there is no filler or repetition.

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 tool with only 5 parameters, an output schema, and no nested objects, the description fully covers field requirements, eligibility logic, statuses, and activation flow. Nothing important is missing for an agent to decide on and invoke the call correctly.

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 baseline is 3. The description reinforces which fields are required and communicates that contact_email drives the first-post-free rule, but it does not add substantial parameter-level meaning beyond what the schema already documents.

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

Purpose4/5

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

The description clearly indicates the tool's purpose: delegating software-solvable-inadequate work to humans and posting a task. It states concrete examples of when to use it, such as phone calls and real-world photos, but it does not explicitly distinguish post_task from the sibling tools hire_human and post_human_task.

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?

The description gives an explicit, actionable trigger condition: call this when the AI agent is stuck on work software cannot do. It effectively says when-not to use it by restricting to things software cannot do, but it does not name alternatives or provide explicit exclusions, so it stops short of a 5.

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

All Invoke — hire a human from your AI agent (first post free) 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

A3.7/5.0

Disambiguation1/5

All three tools are aliases for the same post_task operation, so there is no meaningful distinction between them. An agent choosing among hire_human, post_human_task, and post_task is selecting the same action under different names.

Naming Consistency2/5

The names all use a verb_noun shape, but the verbs differ (hire vs post) and the nouns are inconsistent (human, human_task, task). The pattern is not predictable and the names suggest different operations rather than aliases.

Tool Count2/5

Three tools may seem like a reasonable count, but they expose only one underlying operation. The aliases inflate the surface and make the server feel redundant; a single well-named post_task tool would be more appropriate.

Completeness5/5

For the stated domain of posting a task for a human, the operation covers creation, first-post fee waiver, payment flow, and returns a live task URL. Task management such as update or cancel is outside the declared purpose, so no obvious gap exists.

Resources

Need Help?