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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and closed-world behavior, so the trailing "Read-only" adds nothing. What the description does add beyond the annotations is invocation context: this is a UI-driven call, not a model-driven one. It does not explain what the card's status values mean or the shape/pagination of the reels list, so it goes only modestly beyond structured data.

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 trigger condition is front-loaded and the whole definition is two sentences with no filler. The first sentence is heavily loaded with a nested list of payload fields, which makes it slightly dense, but nothing is wasted.

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 usefully summarizes the returned payload (status, niche, market, numbered reels with covers), which is the right compensation. The one real hole is the undocumented optional filters, which an agent would need to set correctly for this to work when it does populate them.

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 0% and only search_id is given meaning (a single niche search of the connected account). The three optional parameters with enums — kind (all/outlier/stable), view (open/poll) and period (week/month) — are entirely unexplained, so the agent has no basis for choosing values or defaults.

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 description names a concrete verb (fetch data for the niche search card) and enumerates the payload: status, niche, market, and numbered reels with cover images for one niche search of the connected account. The keying by search_id ties it to a single resource. It stops short of naming a sibling, but the domain and scope are unambiguous.

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?

"Use this when the niche search card in the chat needs its data" gives an explicit trigger condition, and "Called by the card itself, not by the model" is a strong exclusion that an agent can act on. It does not name an alternative such as find_viral_in_niche for model-initiated niche exploration, which is the remaining gap.

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