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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds one meaningful behavioral detail — the metric is computed as a relative comparison against the prior window — but says nothing about ranking, thresholds, or how many rows come back.

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?

A single tight sentence that leads with the resource and enumerates the contributing signals; nothing is wasted. It is perhaps slightly too compressed given the surface area the tool actually exposes.

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 values need not be explained, but a 17-parameter, zero-required tool with no parameter documentation and no usage framing leaves substantial gaps. The description is not sufficient to invoke this tool confidently.

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% across 17 parameters, so the description carries the full burden and fails it. An agent cannot tell what distinguishes url from site_url, ad_account from client_id, or range_preset from date_from/date_to, nor how sort_by and activity_only shape results.

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 analytical concept (ad/creative fatigue) and pins it to concrete signals: frequency plus CTR/CPA/ROAS decay versus a prior window. This is far more than a restatement of the name and lets an agent recognise it as a diagnostic metric tool, though it never explicitly separates itself from close siblings like meta_insights_get_fatigue or google_ads_get_fatigue.

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?

No when-to-use guidance, no prerequisites, and no routing to alternatives. With three near-identical 'fatigue' siblings in the list, this is a real omission — the agent gets no signal for choosing meta_ads_get_fatigue over meta_insights_get_fatigue.

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