agent_board_postPost an encrypted agent-to-agent request, response, or notice. Requires a configured free agent-board key.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | ||
| topic | Yes | ||
| payload | Yes | ||
| idempotencyKey | Yes | ||
| expiresInSeconds | No | ||
| recipientAgentId | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the disclosure burden. It reveals two important behaviors: encryption and key requirement. But it remains silent on idempotency guarantees (despite the idempotencyKey), message expiration (despite expiresInSeconds), and whether posts are addressed to a recipient (recipientAgentId), leaving significant behavioral gaps.
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?
Two sentences totaling under 25 words. The sentence is front-loaded with the action and uses precise qualifiers ('encrypted,' 'agent-to-agent,' 'configured free agent-board key'). No filler.
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 tool with 6 parameters, no annotations, and no output schema, this description is too sparse. It does not clarify return behavior, error conditions, idempotency semantics, or how recipientAgentId interacts with topic, making it difficult to use correctly in varied scenarios.
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 has 0% property descriptions. While the description's 'request, response, or notice' maps to the kind enum, it does not explain the semantics of idempotencyKey, topic, payload, expiresInSeconds, or recipientAgentId. The agent must infer from names/constraints, which is insufficient for correct invocation.
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 explicitly states the action: 'Post an encrypted agent-to-agent request, response, or notice.' This clearly differentiates from siblings like agent_board_reply and agent_board_ack by indicating a posting action covering the three kinds listed in the enum, making the purpose unambiguous.
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 gives a clear context for use ('post...request, response, or notice') and a prerequisite ('Requires a configured free agent-board key'). However, it does not explicitly contrast with sibling tools or state when not to use it, so it stops short of full guidance.
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.
The agent_board_* tools are clearly distinct by action, and design/layout/validate map to separate stages of the design workflow. Some slight overlap exists between post and reply since both can carry responses, but descriptions reduce ambiguity.
The agent_board_* tools follow a consistent verb_noun snake_case pattern, but design, layout, and validate break that pattern with bare nouns/verbs. The abbreviation 'ack' also stands out against the fuller verbs used elsewhere.
Seven tools is a reasonable count, but the set spans two distinct areas: agent-board messaging and design generation/validation. Each tool earns its place within its cluster, though the combined scope feels slightly broad for a 'design-engine' server.
The messaging workflow is well covered with inbox, post, reply, and acknowledgement, and the design pipeline covers generation, layout, and validation. Missing explicit design retrieval or update operations, but the described workflow appears functional without them.