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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false), the description discloses the billing model (Embers charged), the failure policy (failed runs refunded), the write scope required, and explicitly what is NOT mutated (no ad, budget or campaign). That is precisely the cost/failure/side-effect information an agent cannot get from the schema or annotations.

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?

Roughly three compact clauses: scope/charge signal first, then the cost precondition, then the no-side-effects assurance, with the endpoint note bracketed at the end. No filler, and the most decision-relevant information (write scope, Embers cost) is 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?

For a 3-parameter mutation with no output schema, it covers cost, refund behavior, prerequisites and non-effects. The remaining gap is what the call returns and how the saved report is subsequently retrieved (presumably via ads_deep_dive_get), which the description leaves implicit.

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 67% and snapshotId is undocumented in the schema, but the description clarifies it must be a 'saved snapshot'. Most valuable is the added meaning for confirmEmbers: it is not just a number but a value that must equal the current quote total for the charge to fire, which sharpens the schema's vaguer wording.

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: run a deep dive on a saved snapshot and save the report. The parenthetical '(Wraps POST /api/v2/ads/deep-dives.)' plus the 'quote total' reference position it correctly relative to ads_deep_dive_quote, ads_deep_dive_get and ads_deep_dive_compare, though no sibling is named outright.

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 confirmEmbers contract ('Charges Embers only when confirmEmbers equals the current quote total') effectively tells the agent it must obtain a quote before running, which is a real sequencing prerequisite. It also rules out ad/budget/campaign impact. What it lacks is an explicit 'use ads_deep_dive_quote first' / 'use ads_deep_dive_get to read instead' statement, leaving routing to inference.

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