advertiser_summary

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

With no annotations provided, the description carries the full burden and delivers: it discloses the sampling behavior ('Fetches a sample of the advertiser's creatives'), the cost model ('Roughly one to two requests per creative'), and the non-opinionated nature ('Pure aggregation — read strategy into it yourself'). It does not cover error handling for unknown advertisers, but the core behaviors are transparent.

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?

Front-loaded one-line summary, then a detailed aggregation list, then an Args/Returns block. Every sentence adds information, and the Args documentation is justified because the schema has no parameter descriptions. Slightly long, but well-organized with critical scope info first.

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 2-parameter tool with no annotations and no output schema, the description compensates well by including an explicit Returns section listing the full result shape (status, advertiser_id, sampled, by_format, etc.). The only gap is failure behavior for unknown advertiser ids, which is minor for a read-only summary tool.

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%, so the description fully compensates: it documents advertiser's three accepted formats (id 'AR...', domain, name) and sample's default (50), maximum (100), and per-creative request cost. This is exactly the semantic information the input schema omits.

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 ('Summarise') and resource ('one advertiser') and enumerates the three aggregation outputs (format mix, copy sample, destinations). The detailed list of what is aggregated (headlines, descriptions, CTA labels, destination hosts) distinguishes it from siblings like compare_advertisers (multiple advertisers), get_ads/get_ad_detail (single ad retrieval), and search_advertisers (finding advertisers).

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?

The scope 'Summarise one advertiser' and the disclaimer 'Pure aggregation — read strategy into it yourself' imply the tool is for read-style analysis of a single advertiser rather than decision-making. However, it never explicitly names a sibling alternative or states when not to use it (e.g., versus compare_advertisers for comparing multiple advertisers); the usage context is implied, not stated.

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