Post a task (custodial escrow default): returns a per-task deposit address; send budget there to fund. Optional owner pubkey receives refunds and can approve.
| Name | Required | Description | Default |
|---|---|---|---|
| spec | Yes | ||
| nonce | Yes | ||
| owner | No | optional Solana pubkey: receives refunds and may accept/dispute/read chat (e.g. the human funding the task) | |
| title | Yes | ||
| budget | Yes | ||
| wallet | Yes | ||
| currency | No | ||
| deadline | Yes | ||
| signature | Yes | ||
| dispute_mode | No | ||
| review_timeout | No | ||
| dispute_timeout | No |
Changes observed during successful MCP inspections.
Input schema / properties / ownerAdded value: +{
+ "description": "optional Solana pubkey: receives refunds and may accept/dispute/read chat (e.g. the human funding the task)",
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does disclose the important escrow flow: a per-task deposit address is returned and budget must be sent there to fund, and the optional owner can receive refunds and approve. That is meaningful behavioral context. But it omits what happens after funding, dispute/timeout resolution, and the effects of the mutation, so significant behavior remains undisclosed.
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?
A compact two-clause sentence that front-loads the core purpose and immediately follows with the funding mechanism. No filler, though it could have spent one clause on the sibling distinction.
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?
A 12-parameter mutation tool with no annotations and no output schema needs far more than this. The deposit-address return is covered, but the majority of required params (nonce, signature, wallet, deadline) and the dispute/timeout configuration are left entirely unexplained.
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?
Schema coverage is only 8% (only 'owner' is documented), so the description must compensate but largely doesn't. It restates the owner role and implies the relationship between 'budget' and the deposit address, but says nothing about wallet, nonce, signature, deadline, currency, spec, dispute_mode, or the two timeout params.
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?
States a specific verb+resource ('Post a task') and adds the key mechanism (custodial escrow, deposit address). However it never distinguishes itself from the near-identical sibling post_task_for_offers, so the agent cannot tell which posting tool to choose from the text alone.
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?
No when-to-use guidance, prerequisites, or alternatives are given. The obvious sibling post_task_for_offers (and the offer/accept workflow) is never referenced, leaving the agent to infer selection from sibling names.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.