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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is covered. The description adds value beyond that by disclosing the shape of the result (a total, a count of contributing ads, and a maximum) and by scoping the number to sub-card ads, which is behavior an agent cannot get from the schema. It stops short of noting currency, units, or whether the window is capped, which keeps it below a 5.

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?

Three sentences, front-loaded with the definition before the usage routing, and no filler. The opening sentence is dense with domain jargon ('sub-floor', 'produced a card', 'target ROAS'), which forces a re-read but is necessary to define the metric precisely. Minor structural cost, no wasted clauses.

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?

There is no output schema, so the description must convey what comes back, and it does: the total, the count of ads, and the largest single one. Combined with fully documented date-window parameters and a complete annotation set, an agent has enough to call it correctly. Gaps are modest — no statement of currency/units or whether results are bounded by the date range only.

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 100%, with site_id, start_date, and end_date all documented including UUID provenance and defaulting rules, so the schema carries parameter meaning. The description adds only the implicit notion that the sum covers a time window and the whole account; it gives no additional syntax or format detail. Baseline 3 applies when the schema does the heavy lifting.

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 names the exact metric ('ad spend the site is losing against its target ROAS on ads too small to have produced a card'), the aggregation scope ('summed across the account'), and the three components returned (total, ad count, biggest single one). It also explicitly separates itself from carded findings, so an agent can distinguish it from list_opportunities and get_report without opening any schema.

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?

It gives an explicit trigger ('Use when asked where paid money is leaking beyond the flagged ads') and names the alternative route for the adjacent case ('Carded findings come from list_opportunities and get_report instead'). The when-to-use and the when-to-use-something-else are both stated rather than inferred.

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