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

Annotations only give a coarse safety profile (not read-only, non-destructive, idempotent), and the description adds genuinely new behavior: creation has no spend impact, names must be unique per account, and amounts above 50/day require allowLargeChange. The uniqueness rule also usefully explains why repeated identical calls will fail rather than duplicate. Missing: what the tool returns (a budget id?) and whether linking can be undone.

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?

Five short sentences: purpose first, then the no-spend guarantee, the linking dependency, the uniqueness constraint, and the two conditional flags. No filler and the most decision-relevant facts are front-loaded.

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?

There is no output schema, so an agent does not learn what comes back from a successful create (presumably an id needed for msads_set_campaign_budget_link) — a modest gap for a create tool. Otherwise the definition covers the mutation's effects, prerequisites, validation thresholds, and the dryRun escape hatch, which is complete relative to the available annotations.

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 baseline is 3, but the description adds meaning the schema does not carry: the concrete '>50 per day needs allowLargeChange' rule for the creation case, whereas the schema only frames allowLargeChange as a relative doubling check against a current value. It also signals dryRun as a review mechanism. Two parameters (accountId, name) get no extra description beyond 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: 'Create a shared daily budget that several campaigns can draw on.' That distinguishes it from campaign-level budget tools by the word 'shared', and it names the follow-up tool msads_set_campaign_budget_link. It never explicitly contrasts itself with msads_create_campaign or msads_set_shared_budget_amount, so sibling differentiation is only implied.

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?

Gives real usage context: creating the budget spends nothing, it only takes effect once linked via msads_set_campaign_budget_link, and dryRun should be used to review first. That is a clear when-to-use and a prerequisite. It stops short of saying when an agent should prefer a non-shared budget or how it relates to msads_set_shared_budget_amount.

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