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

Beyond the annotations, it discloses real operational traits: existing account lines are replaced rather than appended, 'remove' deletes a line, the default span is 12 months, and each call costs $0.001 with no charge on failure. That pricing and failure-cost detail is exactly the kind of context annotations cannot carry. It does not confirm whether the write is reversible.

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?

Information-dense and front-loaded with the core concept before the operational details. It is a long run-on sentence chain, so a reader has to work a bit, but nearly every clause carries unique semantics rather than restating the schema.

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 5-parameter mutation tool with no output schema and only hint-level annotations, the description covers the domain model, line semantics, cost, and the natural follow-up report. Missing pieces are the meaning of new_name and what the call returns, but neither blocks correct invocation.

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 only 40%, so the description has to compensate, and it does for most params: it explains start as the first month, months as an override of the 12-month default, and clarifies the amounts/monthly/yearly/remove line variants. It leaves 'new_name' completely unexplained, which is the main gap for a rename path on a non-idempotent save.

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 thoroughly explains what a budget is and how its lines work, and the title 'Save a budget' supplies the verb. It clearly distinguishes this from books_list_budgets, books_delete_budget and books_report. The only shortfall is that the create-vs-update nature is left implicit in the body text rather than stated outright.

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?

It names the downstream comparison tool explicitly ('Hold it against what happened with books_report budget_variance') and blocks a plausible misuse case ('Not a team's spending budget at Conecto'). It also signals upsert semantics via 'Matched by name'. It stops short of enumerating when to use this versus books_save_accounts or books_setup.

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