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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so 'Saves nothing' is largely redundant. However, the warning that the available figure ignores warm-up limits and recent sends is real behavioral context the annotations cannot express, and it directly prevents misinterpreting the output as a send guarantee.

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?

The first sentence is well front-loaded and informative, but the ending repeats itself almost verbatim ('Saves nothing. It saves nothing, so it can be repeated.'), wasting a full clause. The bare token 'available' is also used without tying it to a returned field.

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?

With no output schema, the description does the right thing by naming the three returned numbers (capacity, reserved share, unreserved remainder). But for a nested four-field request body it says nothing about inputs, and it never mentions the up-to-40-account limit or what happens with sending_days=null.

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% and the single top-level parameter is a nested body with four inner fields, none documented in the schema. The description never explains account_ids, sending_days, strategy_id, or include_delivery_snapshot, so an agent gets no help on what to pass or what 'selected sender' and 'daily' map to.

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 and resource: it shows each selected sender's daily message capacity, the share other campaigns reserved, and the remainder — clearly an allocation preview rather than a read of the whole account list. It is distinguishable from getSendForecast or checkAudienceAvailability by the per-sender allocation framing, though it never names a nearest sibling to sharpen the boundary.

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?

'before saving allocations' implies the call belongs in an allocation-planning flow, and 'it can be repeated' signals it is safe to re-run. There is no explicit when-not guidance and no named alternative (e.g. listSendingAccounts for raw account data), so timing must be inferred.

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