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

Adds substantial context beyond the annotations: the server-side scheduler computes all dates from durations/dependencies/calendar, durations are working days already adjusted for assignee availability, validation failures abort the whole creation with a problem list, and the tool is explicitly non-idempotent ('calling it twice creates two projects'). The dryRun response contents (calculated finish, deadline met/missed, conflicts, overloads, critical path) are spelled out, which annotations alone could never convey.

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, front-loaded with the payload scope, then the scheduling model, then validation, then dryRun/idempotency. Dense but essentially waste-free; the opening sentence is long yet each clause corresponds to a distinct plan section an agent must populate.

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 high-complexity nested mutation tool with no output schema, the description covers the scheduling model, failure behavior, preview contents, permission requirements and idempotency — everything an agent needs to call it safely and interpret the result. Only the exact shape of a successful non-dryRun response is left implicit, which is a minor gap.

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 100%, so the baseline is 3, but the description adds a conceptual rule the schema cannot state: dates are not supplied by the caller and durations are working days accounting for assignee availability. That reframes how every date-ish field in the nested plan should be interpreted, which is real added meaning for a deeply nested schema.

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?

Opens with a specific verb and resource ('Creates a complete new project in one call') and enumerates the full payload it accepts — phases, tasks, milestones, dependencies with lag, constraints, deadlines, people, calendar — so the agent knows exactly what this tool builds. It never names its closest siblings (planitude_create_project, planitude_create_project_from_template), so the distinction must be inferred from the name/title rather than the description.

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?

Gives clear operational guidance on the dryRun flag (preview vs. real creation) and on permissions (write required, read suffices for dryRun), plus a warning that repeat calls create duplicate projects. It does not say when to prefer this over create_project_from_template or plain create_project, which is the main selection decision an agent faces.

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