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

Annotations already establish the safe read profile (readOnlyHint, idempotentHint, non-destructive), and the description adds substantial non-obvious behavior: a hard 92-day window, today's row continuing to count, zero-filled days without activity, failed counts that are never retried, and metrics that read zero before analytics recording began. These are exactly the operational caveats an agent needs and cannot get from annotations or schema.

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 window definition, metric list, and caveats are front-loaded in a dense, well-ordered block, and every clause carries information. It loses a point for restating the title verbatim as the opening line and for a long trailing run of caveats that could be tightened.

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 carries the return-value burden and does so by enumerating the per-day metrics (new conversations, messages, customer mood, escalated/angry conversations, completed actions) plus window totals, along with zero-fill and recording semantics. Nothing an agent needs to call or interpret the result is missing.

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%, so the baseline is 3, but the description goes beyond the schema by bounding both dates ('at most 92 days', 'neither date can be later than today') and stating 'both included' inclusivity semantics. It also cross-references the error behavior for agent_id indirectly through the daily-report framing, though the schema itself carries the 404/403 detail.

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 specific verb (get) and resource (an agent's daily analytics) and immediately defines the shape of the returned data: per-UTC-day rows from `from` to `to` with named metrics. This clearly distinguishes it from siblings like get_agent, get_usage, and list_usage_history, which cover entity data and usage metering rather than conversation analytics.

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?

Usage is implied rather than stated: the 92-day cap, the `to` default, and the note that reading analytics costs no messages hint at when it is appropriate to call. However, it never names an alternative (e.g. get_usage or list_usage_history) or gives an explicit when-not-to-use condition, so the agent must infer the routing.

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