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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered; the description adds genuine behavior beyond that — projection in the account's own time zone, single projection for shared budgets based on combined spend, and what the output flags (over cap vs. unspent budget losing impression share). It does not explain how detail/render/max_findings change the result shape or whether results are truncated, which keeps it off 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?

Front-loaded with the core purpose, then the shared-budget caveat, then the flagging behavior, then the parameter note — every substantive sentence earns its place. The trailing "Tools revision: d80f65c0." is metadata noise that does not help an agent decide or invoke.

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, so return values need not be described, and annotations cover safety; combined with the time-zone and shared-budget semantics this is close to complete for a read-only projection tool. The remaining gap is that the effect of detail/render/max_findings on results is unexplained, which matters for a tool that can emit findings up to a cap.

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 burden; it does resolve the one genuinely ambiguous parameter ("month is YYYY-MM; omit it for this month"). detail, render and max_findings are left to their enum values and defaults, which are largely self-describing, but the description never says what summary vs. full actually contains or what max_findings truncates.

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 opens with a specific verb and resource ("Project this month's spend against each daily budget") and states the aggregation rule that distinguishes it from nearby diagnostics: a shared budget is projected once, on combined spend. An agent can tell this apart from account_health_score or analyze_waste 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 usage context is implied well enough — it's a pacing/overspend-vs-underspend diagnostic, and "omit it for this month" tells the agent the default scope. But it names no alternatives and gives no exclusion guidance (e.g., when to prefer performance_report or analyze_waste instead of pacing), so the agent must infer sibling routing on its own.

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