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

Annotations already declare readOnlyHint and closed-world, and the description adds genuine behavioral nuance: engagement is judged only on posts old enough to have settled, so a viral post or a fresh post won't trigger. It also discloses a secondary return payload (alert rules and email cadence). Missing only things like whether per-account data is scoped to the authenticated user.

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 answer to 'what does this return', and every clause carries information. The second sentence is long and multi-clausal, slightly run-on, but nothing is filler.

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?

No output schema exists, so the description must cover return values, and it does: the alert list with its numbers, the user's alert rules, and email frequency. Combined with the alert-condition definitions and usage triggers, an agent has enough to call it and to format the answer.

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% and the single parameter is already documented, but the description adds the decision rule ('pass the username when they ask about one account') that tells the agent how the optionality maps to conversation context, which the schema alone does not convey.

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?

Opens with a specific question the tool answers ('which tracked accounts need a look right now, and why') and enumerates the exact alert conditions: followers falling, engagement falling, or inactivity. An agent can distinguish it from the stats siblings and from manage_alerts without opening any schema.

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?

Explicitly names the triggering user intents (how an account is doing, what needs attention, check-up, weekly review) and instructs pairing with the stats tools plus the conditional username behavior for single-account questions. This is close to an ideal when-to-use statement.

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