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

Annotations already declare readOnly=true, idempotent=true, destructive=false and openWorld=false, so safety is covered. The description adds non-obvious behavior: supplying period causes days to be ignored and adds a `period` block to the response, and it documents mutual-exclusion constraints. It stops short of describing pagination or output shape.

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 one-line purpose, then a scannable Views block and Args block. Each line earns its place, though defaults and enum values are restated from the schema, which is mild redundancy rather than bloat.

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?

For a 7-parameter read tool with no output schema, the description is nearly self-sufficient: it explains what is returned (overall score, presence rate, historical trend) and how period interacts with the response. Only the undocumented user_intent analytics hint and any result-size/pagination behavior are left unaddressed.

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 14% (just user_intent), so the description carries the semantic load and does it well: brand_id required, view enum meanings, days lookback range 7-365 with default 90, period format YYYY-MM or YYYY-Qn, tag_ids comma-separated, and prompt_id single-prompt filtering. This meaningfully exceeds the bare schema.

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?

Starts with a specific verb+resource ('Get AI visibility scores and trends for a brand over time') and frames itself as the 'how are we doing?' tool, which gives an agent a clear mental model. It names the four views, which scopes what the tool covers. It only partially differentiates from close siblings like get_model_breakdown, get_rankings, or get_perception.

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?

The view list effectively tells the agent when to pick each mode, and the period note explicitly states it 'cannot be combined with tag_ids or prompt_id' and routes whole-month use to get_period_summary. That is strong conditional guidance, though it does not contrast against the broader set of overlapping analytical siblings such as get_model_breakdown.

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