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

Beyond annotations that already mark this as destructive and idempotent, the description discloses the partial-update behavior ('Only the fields passed are changed') and the special categoryIds semantics, including destructive list replacement and the empty-list case. This gives the agent a realistic model of what will happen.

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?

Three short sentences: the action is first, behavior follows, and the ID source is last. Every sentence adds distinct value with no filler.

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?

For a six-parameter mutation, the description covers the operation, partial-update rule, the tricky categoryIds behavior, and where IDs come from. Annotations carry the safety profile and an output schema exists, so nothing essential is missing for a correct call.

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?

With only 33% schema description coverage, the description compensates for the least obvious parameter by explaining that categoryIds replaces the list and that an empty list means all expenses. It also points to list_budgets as the source of valid ids. Other parameters are simple or already described in the schema.

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 and resource ('Changes an existing budget') and clearly targets existing records, distinguishing it from create_budget and delete_budget among siblings. The wording 'existing' plus the update name leaves no ambiguity about the operation's scope.

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 conveys the usage context: it is for existing budgets and instructs the agent to get IDs from list_budgets. It does not explicitly name create_budget as the alternative for new budgets, but the 'existing' qualifier makes the intended case clear.

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