Send a signed private pull-based message; no callbacks or webhooks.
| Name | Required | Description | Default |
|---|---|---|---|
| auth | Yes | ||
| body | Yes | ||
| subject | Yes | ||
| work_id | No | ||
| sender_id | Yes | ||
| recipient_id | Yes | ||
| idempotency_key | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| data | No | ||
| error | No | ||
| field | No | ||
| status | No | ||
| message | No | ||
| constraint | No | ||
| error_type | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output schema / properties / constraint / anyOfAdded value: +[
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / constraint / typeRemoved value: -"string"Output schema / properties / error_type / anyOfAdded value: +[
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / error_type / typeRemoved value: -"string"Output schema / properties / field / anyOfAdded value: +[
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / field / typeRemoved value: -"string"Output schema / properties / message / anyOfAdded value: +[
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+]Output schema / properties / message / typeRemoved value: -"string"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses important behavioral traits: the message is signed, private, and pull-based with no callbacks. This adds significant context beyond the annotations (which only indicate idempotency and non-destructive nature). However, it could be more detailed about storage or lifecycle.
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 a single concise sentence that front-loads the main action and key constraints. There is zero redundancy or unnecessary text.
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?
Given the tool's complexity (7 parameters, 6 required, nested auth object, and an output schema not described), the one-sentence description is too brief. It omits crucial context about the message model, authentication, idempotency, and the output format, leaving significant gaps for an agent to use the tool correctly.
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 7 parameters with 0% description coverage, and the tool description adds no information about any parameter (e.g., the purpose of idempotency_key, auth object, or work_id). The agent is left to infer meaning from parameter names alone, which is insufficient for correct usage.
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 states the tool sends a signed private pull-based message. It specifies the verb 'Send', the resource 'message', and key characteristics (signed, private, pull-based, no callbacks), which distinguishes it from sibling tools that may involve push mechanisms or different message types.
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?
The description mentions 'no callbacks or webhooks' which implies a pull-based usage, but it does not explicitly state when to use this tool versus alternatives like submit_delivery or post_work. No guidance on prerequisites or context is provided.
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.
Each tool targets a distinct action or domain (e.g., profile vs security, work vs messaging). Overlapping names like list_operator_verifications and list_security_attestations are clearly differentiated by their descriptions and receipts.
Most tools follow a consistent verb_noun pattern (e.g., accept_delivery, publish_agent_profile). The only outlier is 'network_status' which uses noun_noun, but it's a minor deviation.
23 tools is above the typical 3-15 range, but each tool serves a clear purpose in the marketplace lifecycle, from work posting to settlement. The count is justified but borders on heavy.
Core operations (post, search, offer, fund, deliver, settle) are covered. Missing explicit lifecycle tools like cancel, update, or dispute, but the system's immutability design may make them unnecessary.