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

Annotations cover the safety profile (readOnly=false, idempotent=false, destructive=false), and the description adds genuinely non-obvious behavior: the auth scope needed, the 409 refusal on duplicate slots, and the fact that site_id/building_id are silently ignored. It does not describe the response shape, but with idempotentHint=false already declared, a duplicate submission failing is consistent and well-explained.

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?

Purpose comes first, then auth, then the cardinality rule and the required fields — a sensible front-loading. It is dense and runs four sentences, but each sentence carries a distinct constraint; only the trailing 'Required:' restatement is partly redundant with 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 7-parameter mutation with no output schema and partial annotation coverage, the description supplies scope, conflict behavior, and the ignored-parameter caveat, which is most of what an agent needs. The only gap is that optional-vs-required for budgeted_amount and allocated_amount is muddled relative to the schema.

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 100%, so the schema already documents every parameter and the baseline is 3; the description earns above baseline by explaining how module, site_id and building_id interact ('the tab does not read site_id or building_id'). Minor flaw: it lists budgeted_amount as Required while the schema requires only year and funding_source.

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 states a concrete verb and resource ('Set an annual funding budget') and grounds it in a real-world referent ('as the dashboard Budget tab does'), which pins down the grain of the record. The specification of one figure per year, per funding source, per workspace distinguishes it from the nearby create_project_budget_item sibling without needing to name it.

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 states the required scope ('budgets:write'), the exact cardinality rule ('Send one row per year and funding source'), an explicit prohibition ('do not split a year across sites or buildings'), and the failure mode if violated (409). An agent can decide whether this is the right tool and how to call it without trial and error.

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