get_recovery_guide

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

With no annotations, the description carries the behavioral burden. It discloses the intended follow-up behavior on every error (read recovery, say userMessageRu, open openUrl in the browser) and states guardrails: never change limits, freeze, auto-topup, or allowlist even on owner orders. This is strong, though it does not explicitly state whether the tool call itself is side-effect-free.

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?

Every sentence earns its place: resource definition, call conditions, required actions, guardrails, exception, and trigger keywords. The most important scope information is front-loaded.

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?

Even without an output schema, the description names the expected return content: RU copy, cabinet deep links, and recovery.openUrl with userMessageRu and openUrl fields. It also gives behavioral guidance, triggers, and guardrails, so an agent can use the result correctly without further detail.

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 input schema has zero parameters and the schema description coverage is 100%, so the baseline is 4. The description adds no parameter details because there are none to document.

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 opens with a specific resource: the full catalog of AgentPay failures, including RU copy, cabinet deep links, and recovery.openUrl. It also ties the tool to concrete user phrases and 4xx errors, which separates it from siblings like get_faq or get_payment_status.

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?

It gives explicit when-to-use conditions: after a failure, when the user asks «что не так» or «почему не купил», before explaining a 4xx, and it lists trigger words. It also provides an exception path to set_test_mode, clearly routing to an alternative.

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