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

With no annotations, the description carries the full behavioral burden. It discloses key operational behavior: recovery auto-accepts only when all blocking machine checks pass, otherwise waits for buyer approval, and the monthly cap and kill switch are rechecked before reserved balance is captured. It still omits permissions, idempotency semantics, and exactly what the kill action destroys.

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?

The description front-loads purpose and behavior, then uses an efficient action-to-endpoint mapping. It is dense with semicolon-separated technical details, but for a five-action tool most sentences earn their place.

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?

Given five actions, no annotations, no output schema, and very low schema description coverage, the definition supplies important behavioral and action/body context. It still leaves authentication, many shared parameters, and mutation side effects undocumented, so an agent cannot resolve every call detail from the definition alone.

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 only 9%, so the description must compensate. It does add meaning for the action values mapped to HTTP methods and for body fields in configure and recover, such as enabled, monthly_cap_usd, callback_url, failed_input, budget_usd, and idempotency_key. But required fields like agent_key and many shared schema properties remain unexplained.

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 states a specific verb set (read, configure, invoke, kill) and resource (unattended recovery for a saved contract), and enumerates the five supported actions. It makes the tool's scope clear, though it does not explicitly distinguish itself from sibling tools such as contract_rerun or unattended_policy.

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 maps each action to an endpoint, which implies when each action should be used, and explains the conditional auto-accept versus buyer-approval behavior. However, it gives no explicit when-to-use guidance against alternatives and no exclusions for when this tool should not be selected.

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