Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description substantially extends the annotations: it reveals the tool is non-blocking ('Returns projectId immediately; niche analysis and asset mapping run async'), prescribes a polling contract ('Poll get_project until niche.analysisStatus is ready'), and discloses the default org behavior ('defaults to the personal organization'). These behaviors are not visible in the annotations (readOnlyHint=false, destructiveHint=false) or the schema, so the description carries the full burden and delivers.

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?

Four sentences of dense, operational prose with no filler. The core action is front-loaded, followed by the async return behavior, the polling instruction, and the siteRelation rule — each sentence earns its place and reads as a crisp runbook.

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 9-param tool with no output schema, the description covers the critical ground: return value ('Returns projectId immediately'), async lifecycle, polling protocol, and the siteRelation decision rule. Gaps remain — the required context param is never mentioned in the description, and the alternative input paths (extras, originType, originInput, originDescription) are silently absent — but the primary workflow an agent needs is fully specified.

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 only 11%, so the description must compensate — and it does for some params: it clarifies website/nicheDescription ('pass either a website URL or a niche description'), defines each siteRelation enum value (mine/client/prospect), and explains organizationId's default. However, it leaves several params undocumented in both schema and description: the required context param, plus extras, originType, originInput, and originDescription. The compensation is partial, not complete.

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 opens with a specific verb and resource — 'Create a new project — pass either a website URL or a niche description (or both)' — and goes on to describe the async flow, making it unmistakable what this tool does. It differentiates itself from siblings by naming get_project as the polling target and list_organizations for org context, so an agent can distinguish it from the many get_/list_ tools nearby.

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 clear operational context: what inputs to provide (website URL, niche description, or both), when to poll get_project, and how to handle siteRelation ('ask only if it is ambiguous, never guess'). It references sibling tools (get_project, list_organizations) for follow-up steps but does not explicitly state when not to use this tool or name direct alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.