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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds crucial context: it is deterministic, does not execute retries, and is a paid resource with a specific price per call. This goes beyond the annotations and informs the agent of side effects and cost.

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 moderately sized and front-loads the core purpose in the first sentence. It then provides usage guidance and cost information without excessive verbosity. It is well-structured and each sentence adds value.

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 planner tool with no output schema, the description does not specify the structure of the produced retryability decisions or backoff schedule. It also leaves the operations array format ambiguous. While the usage context is clear, the missing output and input detail makes it only partially complete for an agent needing to call it 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 schema has 0% description coverage, and the description does not directly explain the parameters. It mentions inputs like 'operation idempotency, failure classes, attempt limits and latency budget,' which loosely maps to the operations array, but does not clarify the structure or what deadline_ms represents. The description fails to compensate for the lack of schema documentation.

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 clearly states the tool is a 'deterministic retry policy planner' that produces retryability decisions and a backoff schedule, explicitly noting it does not execute retries. This distinguishes it from siblings like timeout_budget_planner or failure_classifier by focusing on retry policy planning.

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?

Provides explicit guidance on when to use: 'Use this tool when turn failure/retry constraints into an explicit retry schedule that avoids retrying non-idempotent or non-retryable operations.' It also gives a clear negative use case: 'Do not use it for unrelated general knowledge or unsupported legal, identity, sanctions, fraud, contractual, or regulatory adjudication.' It does not name alternative tools, but the exclusions are clear enough.

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