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

Annotations already declare readOnly/non-destructive/closed-world, and the description adds substantial behavior beyond that: snapshot rows are newest-first and capped at 500, nextOffset drives paging, blended source de-duplicates engines with the CrunchJunkie scan winning, and a model with no answers returns a note naming its engines. It even flags response-size economics (~60,000 vs a few thousand characters), which is real behavioral disclosure.

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?

It is dense and front-loads the scope and date window before the output breakdown, which is the right order. A few clauses (limit/offset, summary) largely duplicate the schema descriptions, and the long parenthetical cost estimate could be tightened, but there is little true waste.

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 10 optional parameters and no output schema, the description carries the full burden and does so: it maps the return payload section by section, explains howToRead for definitions and cautions, and covers the empty-model edge case and response-size tradeoff. An agent can call this correctly and interpret the result without further context.

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, but the description adds meaning not in the schema: the window is whole UTC days capped at 180, limit/offset apply only to snapshots while pooled always covers every row, and summary:true suppresses snapshots. That is genuine added semantics rather than restatement.

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 names the resource precisely: brand and competitor visibility in AI answers over a whole-UTC-day window, and the description enumerates the returned structures (pooled.brands, pooled.clientByEngine, snapshots). It is slightly opaque as a fragment rather than a verb+resource statement and never names close siblings like get_visibility_trend or get_brand_perception to differentiate itself.

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 concrete operational context: default last 30 days, hard cap of 180, use summary:true when a busy month would otherwise return ~60,000 characters, and use limit/offset with nextOffset to page snapshots. It stops short of stating when to prefer this over sibling analytics tools, so there are clear context cues but no exclusions.

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