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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description nonetheless adds substantive behavior: tasks lacking three-point estimates fall back to the project's default range, and passed parameters apply to this call only rather than persisting. It also enumerates the returned artifacts (P50/P80/P95, probability of meeting deadline, cumulative curve, sensitivity/criticality drivers), which is valuable given there is no output schema.

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-loaded with purpose and use case, then mechanism, then outputs, then defaults — a sensible ordering with no filler. Minor redundancy: 'Read-only: nothing is saved' restates readOnlyHint, and the output enumeration is long, though justified by the absence of an output schema.

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 7-parameter simulation tool with no output schema, the description supplies the missing return-value documentation, the estimation fallback rules, parameter persistence semantics and the read-only guarantee. An agent has everything needed to decide on and invoke the call correctly.

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 genuinely non-schema semantic rule: omitted parameters inherit values saved in the plan while passed values apply to this call only. It also clarifies the fallback semantics of the optimistic/pessimistic percentage defaults for tasks without three-point estimates.

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: 'Monte Carlo simulation of the project finish date', then states the mechanism (rescheduling thousands of times with PERT/triangular durations). It is clearly distinct from sibling tools such as planitude_critical_path, planitude_reschedule and planitude_delay_impact.

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?

Frames the use case as answering two concrete questions ('how likely are we to finish by the deadline?', 'which date can we commit to?'), which tells an agent when this simulation is the right choice. It gives no explicit exclusions or pointer to a sibling (e.g., deterministic critical-path analysis), 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.