get_stats

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

Annotations already declare readOnlyHint=true, covering the read-only nature. The description adds the time-window filtering behavior, which is a useful nuance, but it does not disclose details like response format, pagination, or potential rate limits. Since annotations carry the safety profile, the description adds moderate value without contradiction.

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 no filler. It states the primary function first (message counters), then the optional filter. Every word earns its place, making it highly concise and easy to scan.

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 simple read-only aggregation tool with two optional parameters and no output schema, the description is adequate. It tells what is returned (counters) and how to optionally constrain by time. Minor omissions like inclusive/exclusive bounds or return field names are typical and not critical for correct invocation. The combination of schema and description is sufficient.

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 coverage is 100% — both 'to' and 'from' have descriptions ('Window end' and 'Window start') with ISO 8601 format. The description references 'created_at time window' but does not add new semantics beyond restating the schema's intent. Baseline 3 is appropriate given the schema fully explains the parameters.

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 clearly states the tool returns message counters (sent, pending, bounced, opens, clicks, etc.) and optionally supports time-window filtering. It identifies the specific verb ('get') and resource ('message counters'), making the purpose clear. However, it does not explicitly distinguish itself from sibling tools like list_emails or list_bounces, though its aggregated nature makes it sufficiently distinct.

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?

The description provides no guidance on when to use this tool versus alternatives. There is no mention of 'use this for summary counts' or 'for detailed message records use list_emails'. An agent must infer usage context from the name and description alone, lacking explicit routing or exclusions.

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