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

Annotations only indicate non-readOnly, non-idempotent, non-destructive, and openWorldHint. The description adds the default behavior for period and start_date, the limitation that rollover is only for monthly budgets, and the behavior of name defaulting to category name. These are useful behavioral details that go beyond the annotations, though it does not explicitly state side effects like potential creation of a category if not exists, which is why it's not a 5.

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 well-structured with a clear Args list and Returns section. It is slightly verbose due to the detailed explanation of each parameter, but this is justified given the absence of schema descriptions. The information is front-loaded with the core purpose before details, and every line adds value.

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 all six parameters, their defaults, constraints, and edge cases (rollover limited to monthly). It also explains the return value meaning. There is no output schema, but the description does a good job. It is slightly lacking in that it does not mention whether the tool checks for existing budgets or potential conflicts, but overall it is fairly complete.

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?

Even though schema description coverage is 0%, the description explicitly defines each parameter in the Args list, including constraints (minimum amount, valid period options, date format, and the special behavior of name). This adds meaning beyond the schema, which only provides types and defaults. It compensates well for the lack of schema descriptions, though not for nested semantics.

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 clearly states the verb 'create' and the resource 'budget for an expense category', which is specific and actionable. It is distinct from siblings like create_category and create_goal, and the inclusion of 'create a budget' makes it unambiguous.

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 provides detailed parameter semantics including the purpose of the optional display name, which helps distinguish when to use this tool over creating a new category. It also implies the use case for multiple visibly-distinct budgets, effectively explaining when a user would want to use this tool instead of creating a category.

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