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

Beyond the minimal annotations, the description discloses key behaviors: it requires specific authority and confirmation, will return a permission error for scoped child keys, and does not support raising or deleting. This gives the agent a clear model of how the tool behaves under different conditions.

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 concise and well-structured, with each sentence contributing distinct information: action, behavior, authorization, edge case, and exclusions. It is slightly repetitive with 'ADD' and 'safe direction', but overall it avoids unnecessary detail and reads efficiently.

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?

The description covers the core context: what the tool does, required authorization and confirmation, permission failure handling, and explicit exclusions. It does not mention the success response or return value, but since no output schema exists, this is not a major gap; the provided context is sufficient for an agent to decide when and how to invoke it.

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 schema already describes 4 of 5 parameters in detail (80% coverage), including enum meanings for scope_type and the behavior of strict_mode. The narrative adds no significant new parameter semantics beyond reinforcing that confirm must be true, so the baseline score of 3 is appropriate.

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 immediately states 'Create a new hierarchical budget' and clarifies its role as the only mutating tool exposed, which distinguishes it from the read-only sibling tools. It also explicitly notes that raising or deleting budgets is not available, removing ambiguity about its purpose.

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 description gives explicit when-to-use instructions: create a budget to ADD a spending restriction, and requires owner/admin authority plus confirm:true. It also states when not to use it (for raising/deleting budgets) and provides a fallback for permission errors ('propose the budget to the human instead of retrying'), which is clear operational guidance.

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