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

Annotations already cover read-only/idempotent/non-destructive, so the description earns credit for adding real behavior: time-zone-normalized projection, de-duplication of budgets shared by multiple campaigns, and precisely what the flags mean. "Read-only." merely restates an annotation, so not a full 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 tight, front-loaded sentences that lead with the projection logic and follow with flag semantics and the month format. Minor waste: "Read-only." repeats annotations and the "Tools revision" trailer adds nothing for an agent selecting or calling the tool.

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?

An output schema exists and the tool is read-only, so return format and safety need no elaboration. However, with 0% schema coverage on five parameters, the missing semantics for detail/render/max_findings are a real gap for correct invocation.

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 carries the full burden, yet it explains only month (YYYY-MM, omit for current month). The detail, render, max_findings, and customer_id parameters — including two enums — are left entirely undocumented outside their field names.

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 — projecting this month's spend against each daily budget — with precise scope (account's own time zone, shared budgets projected once on combined spend). No sibling does pacing projection, so an agent can distinguish it from analyze_waste or full_audit without opening the 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?

The description implies when the tool is useful ("Flags budgets heading past their cap or leaving money unspent while losing impression share") and explains the month parameter, but never names an alternative tool or states exclusions. Guidance is implied rather than explicit.

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