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

Annotations already cover readOnly/destructive/openWorld, so the bar is lower, and the description still adds substantive context: the numbers come from what Go Shift stores, they are refreshed every few hours, and the reply itself reports when. It also discloses the fan-out behavior when folder is omitted. It does not explain how the state colours are thresholded, which is the one behavioral detail an agent might need when interpreting results.

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?

It is front-loaded with the returned metrics, then the data-source and freshness caveat, then scoping, then the read-only tag — a sensible order with no filler sentences. The metric enumeration is long but each item is a distinct return field, so it earns its space rather than 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?

There is no output schema, so the description carries the burden of describing the return payload, and it does so field by field including the period-end forecast and run-out date. It also covers freshness and the all-clients case. What is missing is any definition of the green/yellow/red/grey state semantics, which an agent would otherwise have to guess when reporting status.

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 exceeds that by defining the semantics of omitting folder — every client that has a budget — which the schema only marks as "Optional." The language parameter is left entirely to the schema, which is acceptable at full coverage.

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 states concretely what the tool returns: spent, % used, remaining, planned to date, average and needed daily rate, forecast at period end, run-out date and a green/yellow/red/grey state. That is a specific resource with an enumerated payload, so an agent can tell it is a read of client budget status rather than a pacing plan or an alert list. It stops short of naming the near-identical siblings (budget_pacing_plan, budgets_at_risk), which is the only thing separating it from a 5.

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?

"Omit folder to get every client that has a budget" gives real guidance on scoping a call, and "Read-only" signals the safe class of operation. There is no statement of when to prefer this over budget_pacing_plan or budgets_at_risk, which is the key ambiguity given three budget siblings. Usage is therefore implied rather than directed.

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