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

Annotations only declare it a safe, closed-world read; the description goes far beyond by disclosing that score is null on days without a snapshot, that dates are swapped when reversed and clamped when in the future, and that the payload includes an events block explaining moves. That is exactly the behavioral context annotations cannot carry.

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, then return shape, then routing, then edge cases — a logical order with no filler sentences. It is dense and long, but nearly every clause carries a constraint or a return-value fact an agent needs, so the length is largely earned.

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 describe the return value, and it does: app_id, app_title, resolved from/to, history[] of {date, score}, and events {notes, app_updates, store_updates}. Combined with the plan-limit and date-normalization rules, nothing essential for a correct first call 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, and the description still adds real meaning: app_id is the numeric internal ID from list_applications, not the store bundle ID, and from/to are subject to plan-window shortening, swapping, and clamping. It stops short of any format detail for the date strings beyond what the schema already says.

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+resource and scope: daily visibility score history for one application. It also defines what the score means (0-100 discoverability across a stable keyword set) and explicitly distinguishes itself from get_keyword_rank_history and compare_events, so an agent can place it among the siblings without opening a 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?

Explicit routing: 'To measure what followed each event, use compare_events' and 'For one keyword rank over time, use get_keyword_rank_history.' It also covers the default window (last 30 days, shortened by the plan's history window), the failure condition (an explicit start older than the plan returns PLAN_LIMIT), and the 400-day hard cap.

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