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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds that the call is a prerequisite read for escrow design, but says nothing about whether the content is static or dynamic, or whether it reflects live configuration — a minor gap given the output schema exists.

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?

Two sentences, no filler, with the resource and its covered topics front-loaded and the actionable precondition last. Every clause carries information.

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, the description needn't describe return values, and the empty parameter list means no invocation detail is required. The one thing an agent might still wonder — whether the model text is authoritative/configurable or a general primer — is left implicit.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. No parameter-level claims are made that could conflict with the empty schema.

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 and resource (returns the AgentTrust trust model) and enumerates the content it covers: guarantees, residual trust, and proof gates vs AI audit. That distinguishes it from operational siblings like prepare_escrow or evaluate_escrow_work, which act rather than explain, though no sibling is named explicitly.

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?

The closing directive, 'Read this before designing an escrow flow,' gives a concrete precondition for invoking it. There are no explicit exclusions or named alternatives, but for a zero-parameter documentation tool the trigger condition is unambiguous.

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