RECOVER — Decide Safely After a Failed Machine Action

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

With no annotations, the description carries the full burden. It transparently discloses the tool's behavioral outcome (returns a deterministic next action) and enumerates the possible outputs. However, it does not explicitly state that the tool itself is non-mutating or whether it requires any special authentication, leaving some implicit inference. Overall, it provides good context beyond the schema.

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 is tightly written in four sentences: trigger condition, special cases, return value, and exclusion. Every sentence adds distinct value with no redundancy, making it easy to parse quickly.

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 tool with 10 optional parameters, no output schema, and no annotations, the description covers the primary usage context and return values comprehensively. It does not explain how parameters influence the decision, but the schema already details them. Minor gap: no explicit statement about non-mutating behavior, but the 'Returns' wording implies it. Overall, sufficient for an agent to invoke correctly.

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 100% description coverage for all 10 parameters, so the schema already fully documents each parameter. The description adds no parameter-specific guidance, which is acceptable given the baseline of 3 for high schema coverage.

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 explicitly states the tool's purpose: to decide the safest next action after a failure, listing the exact possible outputs (RETRY_NOW, WAIT, etc.). It uses a specific verb and resource scope, clearly differentiating it as a recovery decision tool despite having no siblings.

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 guidelines are explicit and comprehensive: 'Use immediately after... fails and before retrying' and 'Especially use after timeouts, 5xx/429 responses, uncertain execution, or any side-effecting action.' It also states exclusions: 'Do not use before an action or for successful actions.' This provides clear when-to-use and when-not-to-use guidance.

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