forecast_spend

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

With no annotations, the description carries the full burden and does well: it discloses that processing is local with 'nothing is sent anywhere', that input must be a FOCUS 1.x CSV export, and that daily exports of 28+ days are needed for the daily trend. It stops short of saying what happens with shorter or non-daily exports, or whether errors surface as failures.

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?

Four dense sentences plus a use-case list, all front-loaded with the core action and privacy posture first, then outputs, then granularity requirements, then triggers. Every clause adds information and none repeat the schema or annotations.

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 or annotations, the description still tells the agent what comes back: a month-end estimate, multi-month projection with 95% ranges, and a list of fastest-growing services. It is nearly complete for a 2-parameter analytic tool, missing only edge-case behavior for insufficient or irregular data.

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 50%: file_path is documented in the schema, but horizon_months only has bounds and a default with no prose. The description's phrase 'the next months' hints at the horizon but never explains the parameter, its 1-12 range, or that it defaults to 3, so compensation for the coverage gap is only partial.

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 — FinOps forecasting over the user's bill — plus the exact outputs (month-end projection, next months, 95% ranges, fastest-growing services). The 'Use for:' list of concrete questions separates it cleanly from siblings like analyze_bill, detect_bill_anomalies, and find_commitment_gaps, which diagnose rather than project.

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 'Use for:' examples give clear triggering contexts ('what will this month's bill be', 'where is spend heading next quarter', 'what is driving growth'), and the daily-export note implies when month-end estimation is available. No explicit 'not for' clause or named alternative tool, which keeps it from a 5.

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