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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description still adds real value beyond them: nothing is persisted, the result is exact only for a single-task delay (a fidelity limitation), and it operates on the current plan rather than a baseline or simulation.

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?

Front-loads the question the tool answers, then the calculation rule, then the scope constraints. Every sentence carries information; the only minor cost is the somewhat mechanical slack explanation, which is justified because it defines what the returned number means.

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?

With no output schema, the description does disclose the two key return elements: the finish-date movement and the list of affected downstream tasks. It is largely sufficient, though it could say more about how the movement is expressed (days vs dates) or that an empty downstream list means no impact.

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 all four parameters are documented in the schema, including delayMinutes taking precedence over delayDays and the accepted task reference formats. The description only reinforces the delay concept ('N days late') and does not add syntax or unit clarification beyond what the schema states, so the baseline 3 applies.

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 a precise, answerable question ('how much does the project finish move if this task is N days late?') and then names the mechanism (comparison against total slack). This is a specific verb+resource framing that is clearly distinct from siblings like planitude_critical_path or planitude_reschedule.

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 context: read-only calculation on the current plan, exact for a delay on a single task, nothing saved. The implied contrast with mutating siblings (reschedule) is strong but never made explicit, and no alternative is named for multi-task or probabilistic what-if analysis (e.g. monte_carlo).

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