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

Annotations only declare readOnly=false and destructive=false. The description adds substantive behavior beyond that: the project is created asynchronously, projectId returns immediately, niche analysis and asset mapping run in the background, and callers should poll get_project until niche.analysisStatus is ready. This is valuable context not available from annotations.

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, each adding a distinct piece of necessary information: input options, async return, polling guidance, siteRelation handling, and organization default. It is dense and front-loaded with the core action, with no filler, though a bit of extra structure could make it easier to parse.

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 common path is well covered: what to pass, what happens after creation, how to poll, how to handle ownership ambiguity, and the organization default. But with 8 optional parameters, no output schema, and no explanation of the origin*/extras fields, the description is incomplete for non-website and alternative input 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 coverage is 0%, so the description carries the burden for parameter meaning. It explains website, nicheDescription, siteRelation (mine/client/prospect), and organizationId (defaults to personal organization). However, extras, originType, originInput, and originDescription are left undocumented, leaving nearly half of the parameters 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?

States the specific verb and resource ('Create a new project') and distinguishes it from siblings like get_project and list_projects by describing the creation action, input modes, and immediate return of a projectId. The purpose is unmistakable.

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?

Provides clear context on when to pass a website URL vs. a niche description, when to set siteRelation, and when to pass organizationId with its default behavior. It also directs polling to get_project, but it does not explicitly name alternative creation paths or when-not-to-use exclusions.

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