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

Annotations only declare read-only and open-world. The description adds real behavioral value beyond that: credit costs per network (8 Meta, 8/12 Google, 4 LinkedIn/TikTok) and the matched/alternatives resolution semantics are precisely the operational detail an agent needs before calling.

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?

Dense and front-loaded with the platform list and per-network summary up front, then inputs, then resolution behavior, then cost. Every sentence carries information, though the single long sentence is slightly heavy.

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 fully covers what is returned (per-network summary: number of ads, formats, oldest running, plus matched/alternatives). Combined with input forms and cost, an agent has everything needed to call and interpret results.

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 75%, and the description meaningfully augments the advertiser parameter by clarifying accepted forms (company name, website, or an alternative's id) and that website is most precise. Country/platforms defaults are already in the schema, so no credit needed there.

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 verb+resource ('all active ads of a brand or competitor') and enumerates the exact networks covered. This is clearly distinguishable from siblings like search_ads and read_ad, which imply search/read of individual ads rather than a per-network brand summary.

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?

Gives explicit input guidance ('website, the most precise') and a resolution workflow: if 'matched' is the wrong company, tell the user and re-call with the alternative's id. It does not explicitly contrast when to use this over search_ads or read_ad, so not a full 5.

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