what_changed

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

With no annotations, the description carries the full burden and does disclose real behavior: it refreshes data first ('1 + N requests, cached'), compares against a local observation archive that is populated by other tools, and returns a per-seed reason with a rerun date when no baseline exists. It also warns that leaving Google's relative list is not proof of falling demand. It stops short of stating auth/permission needs or result limits.

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 purpose is front-loaded and most content earns its place, but the body is a dense run-on of fragments and internal shorthand ('old:', 'direction_now', 'rank_moves') that forces the reader to decode labels. Readability suffers even though little is truly redundant.

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 shape needn't be explained, and the description still adds semantic meaning for the change categories and the no-baseline case. Combined with the refresh/archive behavior and the seeds/since_days constraints, an agent has enough to invoke it, with geo as the only gap.

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 compensate. It adds two useful constraints absent from the schema: seeds limited to 1-5 and since_days bounded to 1-90. However, the third parameter (geo) is never explained, leaving one of three parameters undocumented in both schema and description.

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?

The opening clause 'What changed for 1-5 seeds since the last snapshot' states a specific comparison/delta operation over a named resource, and the body names the change categories (new_breakouts, new_rising, cooled/dropped, rank_moves, direction_flip). It is clearly distinct from interest_over_time, which it explicitly routes to. The phrasing is cryptic but the purpose is recoverable.

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?

It gives per-outcome action guidance ('investigate now', 'consider', 'review: verify with interest_over_time before retiring, or refresh existing post') and names the alternative tool plus the condition for using it. It does not state when NOT to use this tool at all (e.g., for a single seed vs many), but the routing advice is concrete.

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