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

Annotations already declare idempotentHint=true and destructiveHint=false, and the description reinforces and extends this with a concrete safety guarantee ('nobody can be emailed twice for the same request'), a bounded retry policy (gives up after three attempts), a fallback path, and an auth requirement ('needs a token that allows changes'). This is substantial context beyond the structured fields.

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?

Front-loaded with the core action, then usage trigger, safety, retry limits, and auth needs. Six sentences is slightly long, but each carries distinct information and none is redundant with annotations or schema.

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?

Given an output schema exists and annotations cover the safety profile, the description fills the remaining gaps: trigger conditions, retry ceiling, fallback behavior, and permission requirement. An agent has everything needed to invoke 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?

Schema description coverage is 100% for the single prepare_id parameter, and the schema already explains it is the prepare_id whose email or payment step needs another attempt. The description adds no syntax or format detail beyond what the schema provides, so the baseline of 3 applies.

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 states a specific verb ('try the sending step again') and a precise resource scope ('a change that was already made but whose emails or payment link did not finish going out'), and explicitly differentiates from the change itself ('does NOT redo the change itself, only the sending'). An agent can distinguish this from beleeg_confirm_change and beleeg_prepare_change immediately.

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?

It names the exact trigger condition: use it when a confirm or beleeg_look_up(what: "my_changes") reports delivery_failed or delivery_unknown. It also gives a when-not (don't use it to redo the change) and states the alternative fallback (send from the Beleeg site after three failures).

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