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

Annotations already declare readOnly, idempotent, non-destructive, open-world behavior, so safety is covered. The description adds meaningful value with the caveat that the figures are the spend the signals relate to and not guaranteed savings, preventing output misinterpretation. However it says nothing about the shape of the returned signals or how many are expected.

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?

Two short sentences, front-loaded with the definition, then the interpretation caveat. Every sentence earns its place; minor vagueness from 'over final days' when explicit date parameters exist.

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?

A five-parameter detection tool with no output schema and 40% parameter coverage leaves the two threshold parameters (min_spend, min_clicks) unexplained anywhere, and gives no clue about the structure or volume of returned signals. More was needed given how little structured data exists.

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 only 40%, so the description needs to compensate and does not: date_from/date_to are documented in schema, but min_spend and min_clicks have no schema descriptions and the description never mentions them or the fact that min_spend is a string. Only the vague phrase 'over final days' hints at the date window.

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 detection concept with concrete criteria: campaigns with spend and clicks but no conversions over the final days. An agent can tell this apart conceptually from get_performance or tracking_audit, though the description never names an alternative sibling to distinguish itself from them.

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 explicit when-to-use or when-not-to-use guidance, and no alternatives suggested despite relevant siblings like find_anomalies, compare_periods, and tracking_audit. The rationale is implied by the purpose only.

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