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

Goes well beyond the destructive/idempotent/openWorld annotations: attaching makes the campaign draw from a shared amount, the >2x guard exists and can be overridden deliberately, detaching requires a replacement budget, and the call returns the prior setup so it can be restored. That is exactly the consequence-and-reversibility information an agent needs before a destructive mutation.

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?

Three tight sentences: the action pair, then each action's prerequisite in the same order, then the return value and the dryRun recommendation. Every sentence carries distinct information with no repetition of schema text.

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?

With no output schema, the description steps in to say the prior configuration is returned, and it covers both branches plus the override condition. Minor gaps remain: what happens to the campaign's own budget on attach, and whether detaching requires the campaign to have been on a shared budget first.

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 already 86%, so 3 would be the baseline. The description earns above that by tying parameters to branches — allowLargeChange to the attach case with the >2x trigger, dailyBudget to detach — and by endorsing dryRun before mutating. It doesn't restate accountId or the budget id sources, which the schema already covers.

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 — moving a campaign onto or off a shared budget — and separates the two directions (attach/detach) with their effects. It does not name the closest siblings (msads_set_campaign_budget, msads_set_shared_budget_amount), so an agent must infer the boundary from the title rather than from explicit contrast.

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 clear operational conditions: allowLargeChange is required when the shared amount exceeds double the current budget, and detach needs the campaign's new dailyBudget. It also recommends 'Use dryRun first.' It stops short of saying when to pick this tool over msads_set_campaign_budget or msads_create_shared_budget.

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