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

Goes well beyond the readOnly/idempotent annotations by disclosing that creative breakdowns sample only the top 1,000 ads, that response metadata reports matched vs. sampled counts and full-match aggregate spend, and that zero can mean unavailable estimates. These are exactly the behavioral caveats an agent needs to avoid misreading results.

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 but every sentence carries information — demo scope, filter semantics, the timeframe trap, and sampling limits. It is slightly back-loaded, with the critical timeframe caveat appearing mid-paragraph rather than first, but there is no filler.

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 7-parameter stats tool with no output schema and low schema description coverage, the description supplies the essential context: scope, sampling, and how to interpret zeros. What is missing is minor — no mention of pagination or default sorting behavior.

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?

With schema coverage at only 43%, the description compensates for the highest-risk parameters: page_id as an exact advertiser filter, timeframe as last-seen rather than accrued spend, and the demo restriction on project. It leaves q, category, media_type, and active_only to the schema, but the ambiguous ones are covered.

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 and resource: 'Analyze latest cumulative estimated spend in EUR for your tracked advertisers,' which is distinct from sibling stats tools like get_top_landingpages_stats and listing tools like list_brand_ads. It does not explicitly name the sibling it replaces, so it falls short of a 5.

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?

Provides real operating context (public demo restricted to one advertiser, page_id as an exact filter, timeframe as a last-seen window rather than a spend period), which steers correct use. However, it never states when to choose this tool over get_top_landingpages_stats or list_brand_ads, so selection guidance remains implied.

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