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

Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so safety is covered structurally. The description adds genuinely new context: that a new attempt is spawned and joins the original's retry group, which explains why the call is non-idempotent and what side effect to expect. Minor gap: nothing about failure modes or credit 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?

Three short sentences, each contributing: what it does, when it applies plus the alternative, and what the side effect is. Front-loaded and waste-free.

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 need not be described. For a single-parameter retry tool, the description covers eligibility, alternative routing, and the resulting retry-group relationship — everything needed 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?

Only one parameter (generation_id, UUID) with 0% schema description coverage. The description implies it must identify a failed generation, which is meaningful constraint, but adds no format or sourcing detail (e.g., from list_generations or get_generation). Adequate but thin.

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 (retry) and resource (a failed generation), and explicitly contrasts with generate_with_recipe/generate for the non-failure case. An agent can distinguish this from the many generate_* siblings without reading schemas.

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?

Gives both the when ('only a failed one can be retried') and the when-not with a named alternative ('to make another version of something that worked, call the generate tool again'). This is exactly the routing guidance an agent needs.

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