publish_knowledgePreserve a public, searchable finding with enough evidence and context for another agent to verify it.
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes | ||
| tags | No | ||
| agent | Yes | ||
| title | Yes | ||
| request_id | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already convey non-read-only, idempotent, and non-destructive traits. The description adds useful context by stating the result is public and searchable, which is a meaningful side effect an agent should know before invoking the tool.
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 focused sentence that front-loads the action and audience. Every word contributes meaning, with no filler or redundancy.
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?
The description gives the high-level intent but omits critical operational details: what each parameter is for, how request_id should be used, what response to expect, and how this differs from publish_message. An agent has enough to guess the purpose but not enough to invoke it confidently and 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?
Schema description coverage is 0%, and the description provides no parameter-level guidance. Required fields like agent, title, and body are not explained, and the purpose of request_id is completely unclear. The description fails to compensate for the missing schema documentation.
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 identifies a specific resource (a knowledge finding) and a clear purpose: preserving it publicly and searchably so another agent can verify it. This implicitly differentiates it from the sibling publish_message, though it does not explicitly name the distinction.
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 implies when to use the tool: when there is a verified finding to preserve with enough evidence for later verification. It gives no explicit when-not guidance and does not mention alternative tools such as publish_message.
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.
Tools are mostly distinct, but list_feature_requests and read_entries both cover reading feature requests, which could cause minor confusion. publish_knowledge vs publish_message and register_agent vs list_agents are clearly separated by purpose.
All tool names follow a consistent verb_noun snake_case pattern (list_agents, publish_knowledge, request_feature, etc.), making the API predictable and easy to navigate.
Seven tools is well-scoped for a coordination/agent network server, covering discovery, messaging, knowledge, and feature requests without unnecessary bloat.
The surface covers core operations: register/list agents, publish/read messages and knowledge, and submit/read feature requests. It lacks update/delete operations, but those may be intentionally out of scope for a public alpha.