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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavioral facts: the calculation is deterministic with no LLM, the prose falls back to a template when the AI provider is unavailable, and there is no plan gate. This is exactly the kind of context annotations cannot carry.

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 is front-loaded in the first sentence, which is good. The middle is a long semicolon-chained inventory of return fields that is dense and hard to parse, but with no output schema present most of those field names do earn their place; only occasional redundancy (e.g. re-explaining chainDurationDays) could be trimmed.

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 must explain return values, and it does so exhaustively (ordered critical-task IDs, bottleneck task, projectEnd, durations, computed vs stored finishes, finishesAgree/finishGapCalendarDays, reason codes). Combined with the usage triggers and behavioral notes, an agent has everything needed to call and interpret it.

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 100% for the single parameter (projectId is fully documented in the schema), so the schema already carries the parameter burden. The description adds no format or constraint detail beyond it; baseline 3 applies per the high-coverage rule.

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 specific verb+resource ('Compute the critical path for a project... and return a prose summary') and then defines the term precisely (chain of linked tasks with no float, derived from dependencies/durations/constraints/calendar). It also pre-empts common misinterpretations ('no field on a task puts it on the path, and task priority is unrelated to it'), which cleanly separates it from sibling tools like schedule_health_check, leveling_narrative and get_schedule_risk.

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?

Ends with an explicit trigger list: 'Use when the user asks what is on the critical path, which tasks are critical, why a task is or is not critical, asks for tasks to be made critical, or asks when the project or its critical path finishes.' That is strong positive guidance, but no negative cases or named alternatives (e.g. versus leveling_narrative or schedule_health_check) are given, so it stops short of a 5.

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