Get spend and cost models

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds behavior the annotations cannot convey: full-dump versus paged semantics, the ordering key (network, campaign, ad set, ad, day), and that next_cursor is null on the last page — all directly useful for correct invocation.

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 sentences, front-loaded with the resource list, then the paging contract. Every clause carries information (trigger, ordering, terminal cursor), though the second sentence packs several distinct rules into one dense chain and would scan better split.

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 carries the return-shape burden and does so for the important parts: the four data categories returned, the row ordering, and the next_cursor pagination contract. Minor gaps remain — no mention of auth/scope requirements or row-volume limits for the unpaged path.

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 100%, so the baseline is 3. The description earns above baseline by documenting the cross-parameter rule — any of from, to or cursor turns on paging — which the schema only states per-parameter ('alone it changes nothing') and never as a combined trigger.

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 ('Return') and enumerates the resources returned: imported ad spend, cost models, completeness and spend freshness. An agent can tell it is a read tool over spend data, but nothing in the text distinguishes it from siblings like import_spend, pull_network_spend, set_cost_model or get_attribution_rollup.

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 explains the operational condition that selects full-dump mode versus paged mode ('without from, to or cursor every row comes back at once'), which is real usage guidance. However, it never says when to reach for this tool rather than import_spend, pull_network_spend or get_attribution_rollup, so the choice between siblings is left to inference.

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