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

Annotations only declare readOnly/openWorld/non-idempotent; the description adds real substance on top: failure reporting is per-step, the return carries an `ok` flag and revert reasons, and `share` defaults to 'failure-only' so passing simulations are never published. It could go slightly further on fork conditions or latency, but the mutation-safety and privacy profile is well covered.

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 the action and its precondition, then the invocation constraint, then the check-on-ok contract, then the retry path, then the privacy default. No sentence is filler; each adds a distinct operational fact.

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 still explains the meaningful return surface (`ok`, per-step revert reasons) and the side effect of `share`, which is enough to use the tool correctly. Minor gaps remain around what a fork simulation does not catch, but the essential contract is present.

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 only 50%: `from` and `expiresAt` are documented, `share` is an undocumented enum. The description compensates for the biggest gap by explaining `share`'s default and privacy implication, and clarifies provenance constraints for `steps`/`expiresAt` (must be passed exactly as returned by a build_* tool). The internal step shape remains unexplained, but the schema's required fields plus labels carry much of that.

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 (simulate) on a specific resource (built steps on a Tenderly fork) and names the precondition (owner's address, before anyone signs). It is clearly distinguishable from the sibling build_*/quote_* tools because it consumes their output rather than producing it.

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?

Explicit when-to-use sequencing: call after a build_* tool, pass steps and expiresAt verbatim, check ok, and never ask anyone to sign a failing build. It also names a concrete remediation path (rebuild with forceSwapper: true for swap-route failures) and scopes that remedy to the specific sibling tools where it applies.

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