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

Annotations already declare a non-idempotent, non-read-only write, but the description adds context they cannot: the call recalculates project dates, which affects tasks other than the new one, and a parent that previously had no subtasks becomes a summary task whose dates derive from its subtasks. The duplicate-call warning and the write-permission requirement are exactly the operational facts an agent needs before invoking a mutating tool.

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?

Purpose and the date-recalculation side effect are front-loaded, then placement rules, then units and permission. Every sentence carries information, though the working-days/milestone sentence largely duplicates the schema's type and durationDays descriptions.

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 an 11-parameter mutation tool with no output schema, the description covers placement, side effects, duplication, and permissions well. The notable gap is that it never says what comes back (e.g., the new task's id) even though no output schema exists to supply that, which the agent needs to chain into planitude_update_task or planitude_link_tasks.

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 would be 3, but the description adds precedence and interaction semantics the per-property docs do not: the relative priority of parentTask versus afterTask/beforeTask and the fallback to end-of-top-level when none is supplied. It also restates duration units and the milestone zero-duration rule, which is mild redundancy rather than new meaning.

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 first clause gives a specific verb and resource ("Adds one task to an existing project") and immediately names the side effect ("recalculates the dates"). The word "one" plus the positioning rules make it distinguishable from siblings such as planitude_update_task, planitude_indent_task, or the project-creation tools without opening a schema.

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?

It gives concrete routing rules among the placement parameters: parentTask for a subtask, afterTask/beforeTask among siblings, and none of them for the end of the top level. It also warns "Calling it twice adds two tasks" and states the write-permission prerequisite, but it never names an alternative tool (e.g., update_task for later edits), so there is no explicit when-not guidance.

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