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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds only the pre-generation timing cue and nothing about what the response contains or what 'remaining' means numerically; with no output schema, that gap falls on the description.

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?

One short sentence, front-loaded with the verb and resource, no filler. It is efficient rather than padded, though its brevity contributes to the gaps in other dimensions.

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 tool with no output schema, an undocumented optional parameter, and no annotations covering return behavior, the description is too thin. It doesn't say what a 'prompt unit' is or how the remaining count is returned, leaving the agent unable to interpret the result.

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 optional guest_token parameter is never mentioned in the description. The schema names it but gives no type semantics, format, or reason for passing it, and the description does nothing to compensate.

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 verb (read) and resource (remaining prompt units), but 'prompt units' is ambiguous jargon and the description doesn't clarify whether this is a quota, credit balance, or generation budget. No sibling does anything similar, so differentiation isn't the issue, but the resource itself is underspecified.

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 generating' gives an implied timing condition for calling the tool, which is more than nothing. However, it doesn't state what to do with the result, whether calling is required, or what happens if the allowance is zero.

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