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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, but the description adds real capacity and output context: 1-40 tasks, up to 160 finish-to-start dependencies, three-decimal durations, parallel critical tasks reported, and a CSV schedule included. The remaining gap is error behavior - it doesn't say what happens with cyclic dependencies, unknown predecessor IDs, or duplicate task IDs.

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?

Three sentences, front-loaded with the 'use this when' trigger, then limits, then exclusions. Every clause carries a distinct fact (trigger, capacity, output contents, negative scope) with no filler or repetition.

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 read-only, deterministic calculator with an output schema covering return values and annotations covering the safety profile, the description supplies everything else an agent needs: input basis, capacity limits, output artifacts, and out-of-scope capabilities. Nothing material is missing for correct invocation.

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%, so all three parameters and nested task fields are already documented, which sets the baseline at 3. The description mostly restates schema-level facts (durations, three decimals, forty-task cap); its only genuinely new constraint is the aggregate 160-dependency limit, which is not encoded in the schema, and it adds nothing about unit interplay or ID uniqueness beyond what the schema states.

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 sentence names a specific verb and resource (critical path calculation) and enumerates the concrete outputs: project duration, earliest/latest starts and finishes, and task slack. It also pins the input basis ('explicit durations and dependencies'), so an agent knows exactly what class of request this tool answers.

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 both the trigger condition ('when the user wants a critical path calculation, project duration, earliest/latest task starts and finishes, or task slack') and an explicit exclusion list: no calendar dates, no Gantt charts, no resource leveling, no holidays, no inferred durations. An agent can route to or away from this tool without inference.

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