Publish, list, or read durable project artifacts by reference to share notes, analyses, reviews, and proposals across coding agents. Coordinates shared context via stored IDs.
Publish, list, or read durable project artifacts by reference.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | ||
| title | No | ||
| taskId | No | ||
| content | No | ||
| metadata | No | ||
| createdBy | No | unknown-agent | |
| operation | Yes | ||
| artifactId | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden, and it discloses almost nothing: 'durable' and 'by reference' imply persistence and artifactId-based lookup, but nothing about whether publish mutates state, requires content/kind, overwrites existing artifacts, needs auth, or what a response contains. Too thin for a tool whose operation enum includes a write.
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 single sentence is front-loaded and wastes no words, but for an 8-parameter multi-operation tool this is under-specification rather than true conciseness. There is no structure separating the publish/list/read modes or their distinct parameter needs.
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 8 parameters (including a nested metadata object), two enums, a required operation, no output schema, and no annotations, the description is far too sparse to let an agent invoke any of the three modes correctly. It should at minimum state which parameters apply to which operation.
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?
Eight parameters at 0% schema description coverage, and the description explains none of them. Only 'by reference' loosely gestures at artifactId, and the verbs loosely map to the operation enum; kind, taskId, metadata, createdBy, content, and title are left entirely unexplained.
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 names concrete verbs (publish, list, read) and a concrete resource (durable project artifacts) with a scoping phrase ('by reference'), so an agent knows the tool's domain. It does not differentiate itself from siblings like project_context or change_propose, which overlap in the artifact/knowledge space.
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 three verbs hint at modes, but there is no guidance on when to choose this over project_context, change_propose, or review_request, nor which operation each task maps to. No prerequisites, no exclusions, no alternatives named.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.