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

With annotations already covering read-only, idempotent, and non-destructive semantics, the description goes well beyond them: it discloses that values are estimates, that currencies are converted to base, that category nesting is capped at depth 2, how savings is computed, and precisely how to interpret and relay an 'empty: true' result instead of treating it as an error.

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 core purpose is front-loaded in the first clause and every subsequent sentence carries distinct information (contents, planning-vs-actual caveat, empty-state handling). It is somewhat long and leans on capitalized emphasis to restate the same warning, which costs a little density.

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?

No output schema exists, so the description carries the burden of describing the return payload, and it does so thoroughly (field list, currency normalization, nesting depth, derived total and savings) plus the edge case of missing data. An agent has everything needed to call and interpret 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 tool takes zero parameters, so there is nothing for the description to disambiguate; per the baseline for 0-param tools this is a 4. The description correctly adds no pointless parameter discussion.

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 ('Returns the authenticated user's monthly BUDGET PLAN') and then enumerates exactly what is returned: income, category tree (max depth 2), estimated costs with currency conversion, totals, and potential savings. It explicitly contrasts itself with spending views ('do NOT reflect actual spending'), which is the key distinction from sibling tools like get_accounts or get_net_worth.

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 framing as a 'PLANNING view' versus actual spending gives clear context for when the tool's output is appropriate, and it prescribes handling of the empty-result case (relay message and next_step_url). It stops short of naming which sibling tool to call instead when the user wants actual spend, so routing between siblings is left partly to inference.

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