Say what this product is for, so every run knows what it is building toward.
`vision_md` is free-form markdown and must be non-empty. Tenant-scoped: a
project not in the caller's workspace 404s. Returns {project_id,
product_vision_md, updated_at, next_step}.
| Name | Required | Description | Default |
|---|---|---|---|
| vision_md | Yes | ||
| project_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description adds substantial behavioral details beyond annotations: tenant-scoping ('a project not in the caller's workspace 404s'), the non-emptiness constraint on vision_md, the return shape ({project_id, product_vision_md, updated_at, next_step}), and the purpose 'so every run knows what it is building toward'. Annotations (idempotentHint=true, destructiveHint=false) align with the described behavior, and the description enhances understanding without contradiction.
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 compact (three sentences), with the primary purpose stated upfront in the first line. Code formatting and a newline improve readability. Every clause adds value—constraints, scoping, return type—without redundancy. It is appropriately sized for a 2-parameter tool.
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 covers all critical aspects: what the tool does, field constraints, tenant scope, error behavior, and return structure. It is fully self-contained for an agent to invoke it correctly, especially since the output schema is already declared externally. No further details are needed for typical usage.
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?
With 0% schema coverage, the description compensates by clarifying vision_md as 'free-form markdown' with the 'must be non-empty' constraint. project_id's semantics are only indirectly explained through 'a project not in the caller's workspace', which hints at its identifier nature. While the description does not explicitly enumerate each parameter, it provides functional meaning that goes beyond the field names alone, making this a strong compensation for the lack of 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?
Description clearly states the tool's function: 'Say what this product is for', using a verb-object structure that directly maps to the tool name. It defines the resource (product vision) and differentiates from siblings like set_product_goal by focusing on the vision, not goal. The phrasing is specific and 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?
No explicit guidance on when to use this tool vs. alternatives, nor any mention of when not to use it. While the purpose is implied by the name, there is no discussion of prerequisites, differences from similar tools, or use cases. This is a clear gap given the rich sibling set includes set_product_goal, which could conceptually overlap in intent.
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.
Every tool targets a distinct resource and action duo, even within clusters like request handling or security reviews. The get_ vs run_ pairs are clearly separated, and descriptions explicitly contrast confusing alternatives such as archive_project vs delete_project.
The set overwhelmingly follows verb_noun snake_case (submit_request, list_projects, resolve_escalation). The one visible deviation is project_status, which breaks the get_/pattern, and signup is a single-word verb instead of sign_up.
37 tools is well above the 25+ threshold and spans auth, billing, project lifecycle, roadmap, escalations, product documents, and multiple review types. Most tools earn their place, but the surface is too large for one server and would be more coherent split into focused servers.
The domain coverage is broad: full project lifecycle, request intake/refinement, roadmap manipulation, escalation handling, product doc read/write, and security/legal review flows. Minor gaps exist, most notably no dedicated task-listing or task-update tool, but agents can work around these via project_status and list_escalations.