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

Annotations already declare readOnly/no-destructive/openWorld=false, but the description adds substantial behavioral context beyond them: determinism, the P10-P90 band, named drivers, walk-forward accuracy metrics, and the sufficient_history=false signal for short histories. That is rich disclosure of output character and reliability limits.

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 purpose and scope, then qualifications; each sentence carries distinct information. It is fairly dense and long, but no sentence is redundant padding.

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, yet the description still sketches the return shape (per-currency net, band, drivers, accuracy) and flags the sufficient_history edge case, which is exactly the extra an agent needs to interpret results. Nothing material is missing.

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 both parameters are fully documented in the schema, including the default 8 and the 1-26 range. The description only restates the horizon in prose ('next N weeks, default 8') and never addresses the currency filter, so it adds little beyond the schema baseline.

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+resource (projects expected net cashflow per currency) and immediately scopes it to the user's own settlement history, which cleanly separates it from siblings like get_fx_exposure or get_funding_forecast. The explicit 'NOT an FX-rate prediction' clause further disambiguates.

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?

Gives clear context for when this applies (own settlement history, open invoices, recurring/seasonal flows) and rules out the FX-prediction use case. It does not name a specific sibling alternative to reach for instead, so it stops short of full when-not guidance.

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