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

Annotations already declare destructiveHint=true, idempotentHint=false, and openWorldHint=true, so the agent knows this is an irreversible, non-repeatable write. The description adds useful scope context ('failed recipients' only, not the whole batch), but it omits the key consequence of a non-idempotent retry: that recipients may receive duplicate messages, and whether already-succeeded recipients are skipped.

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?

A single front-loaded sentence with zero filler and the scope qualifier in the right place. It is arguably too terse for a destructive operation, but nothing is wasted.

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 destructive, non-idempotent mutation with no output schema, the description should say what happens after the call (does the batch return to sending, what status results) and warn about duplicate sends. It provides only the one-line scope, leaving the agent without the consequences it needs before invoking an irreversible action.

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?

There is one parameter with 100% schema description coverage ('Batch id'), so the schema fully documents it. The description only implies the id refers to the batch; it adds no format, source, or validation detail beyond what the schema already provides.

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 batch's failed recipients), including the scope limitation that only failures are re-attempted. That distinguishes it from send_batch and cancel_batch, but it does not distinguish it from the closely related resume_batch sibling, which an agent could easily confuse with it.

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?

There is no guidance on when to use this versus alternatives such as resume_batch, send_batch, or cancel_batch, and no preconditions are given. The agent must infer from the name alone when a retry is appropriate.

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