Email Metrics

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

The description accurately reflects a read-only operation, aligning with the readOnlyHint annotation. It adds useful context by stating the response can be totals-only by default and can be broken down by dimensions. However, it doesn't disclose behaviors like defaults for date range (6 days before endDate), default granularity (daily), max 100 IDs, or the mutual exclusions between emailId/broadcastId and dimensions. Those are in the schema, so this is not a contradiction, but the description itself adds limited behavioral depth beyond the annotation.

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 description is a single well-structured sentence that front-loads the core purpose (retrieve metrics), scopes it (account-level), lists the key metric types, and states the available breakdown dimensions. Every element earns its place without redundancy. It is appropriately sized for a read-only analytics tool with rich schema documentation.

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?

The description is complete for an agent's initial selection and invocation: it names the resource, the metric families, the date range, and the optional breakdowns. Combined with 100% schema coverage and the readOnlyHint annotation, the agent has enough to call the tool safely for most cases. A small gap is that the description doesn't mention the default behavior (totals only) or the incompatibilities between parameters, but those are documented in the schema, and there is no output schema or complex nested structure demanding more.

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%, so the baseline is 3. The description adds conceptual meaning by listing the breakdown dimensions (period, domain, email, broadcast) and metric categories, but it doesn't add value beyond what the schema already documents. It does not clarify the mutual exclusion constraints or the meaning of 'defaults to none, which returns totals only' in a way that improves on the parameter descriptions, so it earns the baseline without exceeding it.

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 retrieves account-level email delivery and engagement metrics with a specific verb ('Retrieve') and resource ('account-level email delivery and engagement metrics'). It enumerates the metric types and the optional breakdown dimensions, which distinguishes it from sibling tools like get-email or list-emails. The scope (account-level) and the filtering/breakdown options make the tool's purpose unambiguous.

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 conveys the main use case: retrieving aggregate email metrics for a date range, optionally broken down by period, domain, email, or broadcast. It does not explicitly name sibling alternatives or state when not to use this tool, but the context (read-oriented analytics vs. tools like send-email, list-emails, get-broadcast) makes the intended usage reasonably clear. Slight deduction for lacking explicit exclusion guidance such as 'for per-recipient data use list-broadcast-recipients.'

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