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

Even with readOnlyHint present, the description adds substantial non-obvious behavior: it always returns a probabilistic range rather than a single value, and unresolvable plans come back as advice, not refusal or an error. This is the kind of nuance an agent cannot safely infer from the schema or annotation alone.

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?

The description is compact and front-loads the most important usage signal: 'BEFORE spending.' Each sentence carries distinct information: the purpose, the return shape, the failure-mode behavior, and the scoping mechanism. There is no redundant or filler content.

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?

Even without an output schema, the description covers the return type, its variability, the failure/advice behavior, and how to control scope — which is all an agent needs to invoke and interpret the result correctly. The tool's complexity is low, and this description fully compensates for the absence of structured output definitions.

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?

The input schema already documents both parameters completely, including the meaning of count and the scoping behavior of space_id. The description reinforces this with 'candidate angle count' and 'override for this one call,' but adds little semantic value beyond what the schema already states.

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 a concrete purpose: it simulates the budget-based stopping rule on the account's observed spend, CPC, and CVR, and returns a P20-P80 weeks-to-verdict range for a candidate angle count. The 'BEFORE spending' framing and 'never a single week' caveat make its function distinct from simple read tools like get_angle or get_angle_readout.

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 opening 'BEFORE spending' is a clear usage trigger, and the description gives concrete scoping guidance: use the active Space or pass space_id to override. It does not explicitly name alternatives like get_angle_readout or state when NOT to use the tool, so some inference is still required.

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