whatif

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

Annotations already declare readOnlyHint=true and openWorldHint=false; the description reinforces this with 'Records nothing', which is exactly the trait an agent worries about for a simulation tool. It also discloses the shape of the result (theses reached, links traversed, alert likelihood) beyond what annotations say. It does not mention cost, depth limits, or latency, which is a minor gap.

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 short sentences, no repetition, and the key non-persistence fact is placed last as a memorable closer. The lead rhetorical question is slightly softer than a declarative statement but does establish the counterfactual framing efficiently.

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 an output schema present and annotations covering safety, the description's job is mainly to frame the computation, which it does by naming the three outputs (theses, links, alerts). What is missing is scale/scope guidance (how far the traversal goes) and confirmation that missing entities are tolerated. Adequate but not exhaustive for a graph-simulation tool.

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 75%, so entities and description are already well documented, and the schema explains materiality's default behavior. The description adds no parameter-level meaning, notably nothing about how materiality or occurred_at affect the simulation. Baseline 3 is appropriate given high schema coverage.

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 description names the operation precisely: a hypothetical-event simulation that traces which theses and links the event would reach, and whether it raises alerts. It is clearly distinct from siblings like impact or add_event. The opening rhetorical question costs a little sharpness but the follow-up clauses pin the purpose down.

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?

Usage is only implied by the counterfactual framing; there is no explicit statement of when to prefer this over impact (actual event propagation) or timeline/what_changed. The phrase 'Records nothing' implicitly routes write intents elsewhere, but no alternative is named. An agent can infer the scenario analysis use case, but must read sibling names to confirm.

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