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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds genuinely new context: Regent enforces the policy and injects the credential so the API key never reaches the agent. It stops short of describing what happens when policy denies the call or how responses are shaped.

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 tight sentences with zero filler, and the core scoping constraint (read-only, GET/HEAD/OPTIONS) is front-loaded before the credential-handling note.

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 5-parameter policy-gated proxy with a nested `facts` object and no output schema, the description covers the safety model and credential handling well. It leaves out denial/failure behavior and what a response looks like, which would matter for an agent composing policy-keyed `facts`.

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 80%, so the schema already carries the parameter semantics (path, facts, intent, user_token, method enum). The description only restates the method restriction, adding no new meaning beyond the enum; baseline 3 applies.

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 (read) and a specific resource (https://api.stripe.com) plus the allowed method set, so an agent knows exactly what this tool does. It does not name the `stripe` sibling as the write counterpart, relying on the sentence 'Nothing is changed and no money moves' to draw that line implicitly.

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 strongly implied: use this for GET/HEAD/OPTIONS against Stripe, and anything that changes state or moves money belongs elsewhere. However, the alternative is never named (e.g. `stripe`), and no prerequisites about policy approval or denial handling are stated.

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