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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description does add one genuinely useful behavioral fact — that MCP-level approval requirements are org-configurable while business workflow approvals always apply — which an agent should know before calling. It says nothing about pagination, permissions, or what 'whole budget' includes (line items? history?).

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?

It is short, but the opening sentence is pure filler that restates the product name, and the approval sentence is boilerplate that reads as organizational garnish rather than tool-specific guidance. The one informative phrase ("Read a whole budget") is buried in the middle.

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?

An output schema exists, so return values need not be described. But for a single-parameter lookup in a namespace crowded with budget tools, the description omits the parameter meaning and omits any routing guidance versus siblings, leaving the agent to guess from the name alone.

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 description coverage is 0% and the single required parameter budgetId is undocumented in both the schema and the description. The description never mentions the UUID identifier at all, so an agent gets no guidance on whether it is a budget ID vs a project/site budget ID — a real ambiguity given the many budget sibling tools.

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?

"Read a whole budget" gives a specific verb and resource, distinguishing a full-record fetch from list/summary siblings in spirit. However, it never names the actual alternatives (get_budget_portfolio, get_budget_history, get_budget_committed_amounts, list_project_budget) that an agent must choose between, so differentiation is left implicit.

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 opening clause "Use this when working with RetailHardHat budgets records" is circular — it restates the tool's domain rather than a condition for selection. There is no statement of when to prefer this over list_project_budget or get_budget_committed_amounts, and no prerequisites beyond a generic approval note.

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