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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, setting a baseline. The description adds useful context beyond that: only incomplete members are retried and previously successful files are preserved in place, which clarifies the partially-destructive/partial-progress semantics of a retry operation.

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?

Two short sentences, front-loaded with the action and followed by the key consequence. Zero filler; every sentence earns its 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?

For a one-parameter retry tool with no output schema, the description covers the core action and one important side effect, but omits how to confirm completion (e.g., via get_status) and any guidance about the pack_id input, leaving gaps an agent would have to guess at.

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 single parameter pack_id has 0% schema description coverage and a regex pattern only. The description says nothing about what a pack id is, how to obtain it, or whether retries are per-pack — it provides no compensating meaning for the undocumented parameter.

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 names a specific verb (retry) and resource (incomplete image pack members), so the agent knows exactly what operation this performs. It does not explicitly distinguish itself from sibling retry tools (retry_batch, retry_carousel), though the 'image pack' resource narrows it implicitly.

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 is implied by 'retry incomplete' — an agent would infer this is for packs that failed partway. There is no explicit when-to-use/when-not guidance relative to siblings like create_image_pack or get_status, and no prerequisites or follow-up steps are stated.

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