AgentPMT - Marketplace For Autonomous Agents

AgentPMT Send Human Request

AgentPMT-Send-Human-Request

AgentPMT Send Human Request - Send a request or notification to the human who owns your budget, then check their decision. Every send is delivered to the human by email, by push notification in the AgentPMT mobile app, and as a notice in the Messages tab of the AgentPMT dashboard; they approve or deny from any of the three. Use action=send with request_type enable_tool or credential_setup (id = product ObjectId, required), enable_workflow (id = workflow ObjectId, required), add_funds, other, or notification_only, plus a plain-language request (max 5000 characters). Approving enable_tool or enable_workflow adds the target to the current budget automatically; approving add_funds completes a credit purchase; approving credential_setup stores the connection credentials. send returns mobile_request_id and approval_required. When approval_required is true, poll with action=check_response and request_id until status is approved, denied, or expired, then read decision_notes and action_result before continuing. notification_only never requires approval and must not be polled. Free, no credentials required, always available.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`id`	No	Product/workflow ObjectId for access requests, or optional target identifier for check_response lookup
`action`	No	Operation to perform: send (default) or check_response. Only use check_response when send returned approval_required=true.	send
`request`	No	Freeform request body to send to the user (required when action=send)
`request_id`	No	Mobile approval request ObjectId to check when action=check_response.
`request_type`	No	Request type: add_funds, enable_tool, enable_workflow, notification_only, other (required when action=send). Use notification_only to send a message that does not require approval; do not wait after sending.
`include_request`	No	When action=check_response, include the full request record in the response.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 10, 2026
- addedInput schema / properties / id / default
```
Added value: +null
```
- addedInput schema / properties / request / default
```
Added value: +null
```
- addedInput schema / properties / request_type / default
```
Added value: +null
```
Changed1 schema field changedMay 13, 2026
- addedInput schema / $schema
```
Added value: +"https://json-schema.org/draft/2020-12/schema"
```

Changed2 schema fields changedMar 4, 2026

changedInput schema / properties / action / description

Previous value: -"Operation to perform: send (default) or check_response."New value: +"Operation to perform: send (default) or check_response. Only use check_response when send returned approval_required=true."

changedInput schema / properties / request_type / description

Previous value: -"Request type: add_funds, enable_tool, enable_workflow, notification_only, other (required when action=send). Use notification_only to send a message that does not require approval."New value: +"Request type: add_funds, enable_tool, enable_workflow, notification_only, other (required when action=send). Use notification_only to send a message that does not require approval; do not wait after sending."

First observedFeb 18, 2026

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations to fall back on, the description discloses key behaviors: delivery channels, approval side effects (budget addition, credit purchase, credential storage), return fields, polling statuses, and the fact that notification_only never requires approval. It also states that the tool is free and requires no credentials. This is substantial transparency beyond the schema.

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?

The description is a dense single paragraph with no filler and is front-loaded with the core purpose. It could be slightly easier to scan with bullets or clearer separation between the send flow and check_response flow, but every sentence earns its place.

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?

Despite having no output schema and no annotations, the description provides a complete operational picture: return values, poll loop, statuses, approval consequences, and credential/availability context. An agent has enough information to invoke the tool correctly and handle the async approval flow without guessing.

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

Parameters5/5

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

The description adds critical parameter meaning beyond the schema: id is required for enable_tool/credential_setup and expects a product ObjectId, enable_workflow expects a workflow ObjectId, request has a 5000-character limit, and request_type values control behavior. Even though the schema has 100% coverage of parameter names, the description materially enriches how they should be populated.

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?

The description clearly states the tool's purpose: send a request or notification to the human who owns the budget and then check their decision. It names the resource, the action, and the two operation modes (send/check_response), making it easy to distinguish from sibling tools like issue reporting or workflow creation.

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 explicit procedural guidance: use action=send with specific request types, poll with action=check_response only when approval_required is true, and never poll notification_only. It does not explicitly contrast with sibling tools, but within this tool's own workflow it provides clear when-to-use and when-not-to-use instructions.

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

All AgentPMT - Marketplace For Autonomous Agents tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?