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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the plan gating ("Requires a Basic plan or higher") and the data-provenance caveat that questions in the result are written by visitors. That caveat matters because it warns the agent the text may be noisy or untrusted. It does not discuss volume or cost of the window, so not a 5.

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?

Front-loaded with the core action, then a metric enumeration, use case, eligibility requirement, and caveat. It is dense but every clause carries information; the long enumerations are the main reason it is not maximally tight.

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?

An output schema exists, so return values need not be spelled out, yet the description still previews the result contents and flags plan requirements and visitor-authored text. For a two-parameter read-only aggregation tool, this covers what an agent needs to call and interpret it.

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 50%: agentId is documented in the schema ("Agent ID from list_agents"), while periodDays has bounds and a default but no description. The phrase "over the last N days" loosely ties the description to periodDays but adds no format or behavior detail beyond the schema's minimum/maximum/default.

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 and resource ("Summarize how one agent performed over the last N days") and then enumerates exactly what the summary contains: conversation, visitor message, lead and handoff counts, feedback, opening questions, and disliked answers. This aggregated-performance shape is clearly distinguishable from sibling tools like get_agent (configuration) or list_conversations (raw records).

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?

"Useful for finding common questions and knowledge gaps" gives a concrete use case, and the Basic-plan caveat tells the agent about an eligibility precondition. It stops short of explicit when-not guidance or naming an alternative sibling, so it is clear context rather than full routing guidance.

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