retry_policy

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

Annotations already declare readOnlyHint, idempotentHint, closed-world and non-destructive, and the word 'Compute' is consistent with that safe, pure-calculation profile. The description adds that the output includes deadline-fit analysis and circuit-breaker guidance, which goes slightly beyond the annotations, but says nothing about determinism, limits, or how the guidance is derived.

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?

One sentence, front-loaded with the core action and resource, with the secondary outputs trailing. No filler or repetition.

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?

An output schema exists, so return values needn't be explained, but for a 7-parameter computation with zero schema descriptions and required inputs like operationIdempotent and jitter mode, the definition leaves too much to inference. A brief note on what each knob controls (and that operationIdempotent changes the guidance, not the schedule) would close the gap.

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 0% across 7 parameters (6 required), so the description carries the full burden — yet it explains none of them. baseDelayMs, factor, capMs, maxAttempts, the 'none'/'full'/'equal' jitter enum, deadlineMs and operationIdempotent (which drives the guidance output) are all left for the agent to guess from names alone.

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 and resource ('Compute an exponential backoff schedule with jitter') and enumerates the concrete outputs: worst-case wait, deadline fit, plus idempotency and circuit-breaker guidance. That clearly separates it from every sibling, which are review/plan/document generators rather than a backoff calculator.

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?

The purpose implies when it is useful (sizing retries for an unreliable dependency), but there is no explicit when-to-use, when-not-to-use, or named alternative among siblings. An agent must infer the triggering situation from the one-sentence purpose.

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