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

The description goes far beyond the minimal readOnlyHint=true and destructiveHint=false. It discloses quotas, rate limits (60/min, 1000/hr), concurrency gating for 'heavy' calls, free-plan archive window restrictions, and the meaning of pagination.total_status='restricted'. It even explains that a zero means 'nothing in the archive window', preventing misinterpretation. No contradiction with annotations.

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 description is long but deliberately front-loaded: first sentence states the core purpose, then immediately differentiates alternatives, then dives into quota/rate-limit/concurrency details. Every section serves a real decision the agent faces. While dense, it avoids redundancy and earns its length given the tool's operational complexity.

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 tool with quota, rate limits, concurrency gates, and a free-plan special case, the description covers every conceivable decision point: how to size pages, what errors look like, how to connect an unlinked agent, and what happens when the archive window shrinks. The existence of an output schema means return-value details need not be spelled out. Nothing essential is missing.

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 both parameters are already described in schema. The description adds actionable details beyond schema: query must be ≥2 chars, a link in any form resolves to canonical fanpage with exact match first, limit defaults to 20 but is clamped to 50 upstream (not rejected). These are value-add semantics, not just repetition.

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 opens with a clear verb+resource ('Search advertisers') and specifies exactly the three input forms accepted (name, numeric page id, or pasted link). It explicitly distinguishes itself from siblings: get_advertiser for one full card, search_ads for ads, get_trends for rankings. No ambiguity remains about what this tool does.

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?

Explicit when-to-use versus alternatives is given: 'To fetch ONE advertiser's full card by id use get_advertiser; to see an advertiser's ads, call search_ads with advertiser_id. For advertiser RANKINGS, ordering and filters ... use get_trends with dimension=advertisers.' It also explains when to expect restricted results and how to handle them. This is textbook usage guidance.

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