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

Annotations already declare readOnly/idempotent safety, yet the description still adds substantive behavior: the exact payload (planned vs done over 4 weeks, streak toward 67 days, 8 weeks of history, verdict plus suggestion, latest two-month report) and the ordering ("weakest first") for the list mode. The detail that task_id accepts "any day of the series" is a genuinely non-obvious behavioral fact.

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 definition is front-loaded with the resource and then branches cleanly into the two modes, with no filler sentences. The long comma-chained enumeration of returned data is dense but each item earns its place by describing payload.

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?

There is no output schema, so the description must convey return values, and it enumerates them precisely for both modes including ordering and streak target. For a single optional parameter read-only tool, nothing essential 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 0%, so the description must carry the burden, and it does: task_id is explained as any day of the habit series, and the omitted case is spelled out as a full habit listing. The only gap is that the string ID format and behavior for an invalid/nonexistent id are not stated.

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?

It names a specific resource (habit statistics) and defines a habit as a repeating task, which disambiguates it from the plain task tools in the sibling list. It also splits behavior into two clearly described modes (with vs. without task_id). It never explicitly contrasts itself with get_tasks/get_day_brief, so sibling differentiation is only implicit.

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?

"Fits when the user asks how a habit or their habits are going" gives a clear triggering condition, and the with/without task_id split tells the agent which mode to pick. There is no explicit when-not or exclusion against related tools such as get_tasks, so it stops short of full routing guidance.

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