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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description goes well beyond them: closed months are served from a frozen archive and answer identically later, the open month is MTD with status='open', quarters are derived from three months, and fields_missing tells the agent what to say is 'not reported'. It also discloses that response_format='concise' caps long lists and that deltas are precomputed with correct sign.

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?

Well front-loaded and organized with Views, Examples, and Args sections, and the anti-drift warnings genuinely earn their place. It is on the long side and the Args block partially restates schema-adjacent content, but the length is defensible for an 8-parameter tool with no output schema.

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 still enumerates the return shape (period, prior period, metrics, breakdowns, headline_metric_ids, groups, metric_meta, period.status, period.fields_missing) and explains how deltas, directions, and ranks are already computed. Nothing an agent needs to call it 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 description coverage is only 13%, so the description must carry the semantics, and it does: period format (YYYY-MM / YYYY-Qn, omit for most recent closed month), view contents for each enum value, compare default, include_definitions content, months (list-only, 1-36, default 12), and response_format behavior. Seven of eight parameters are richly documented, far exceeding what the schema provides.

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 ('Get one frozen calendar month or quarter: the whole client report in one call') and explicitly distinguishes itself from rolling/days-window reads. An agent immediately knows this is the canonical calendar-period report tool, not a daily-series tool.

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?

Gives explicit when-to-use ('THE tool for any calendar-month or quarter figure and for a monthly or quarterly client report') plus a clear when-not ('Never approximate a month with days=30 or days=31; the window slides and the figure drifts'). It also tells the agent to use view='list' first to see what is frozen before requesting it, which is real routing guidance.

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