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

Annotations already cover read-only/idempotent/no-writes, yet the description still adds substantive behaviour: 'no writes', 'missing rows are never zero', 'generic results never purchases', the date-fabrication prohibition, and the fact calls consume no credits. These are genuine caveats an agent could not derive from the annotation block.

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?

Front-loaded with the core comparison statement, but the opening "Preferred after reading performance-diagnosis" is cryptic, 'separates facts, unknowns and next verification' is under-explained, and the MCP/credit boilerplate at the tail dilutes the operational content.

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 nested four-parameter diagnostic with no output schema, the description covers the snapshot scope, date discipline, responseMode contract and modelling caveats. Minor gaps remain on what the 'verified report' actually contains and how the two periods' lengths are validated.

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 75%, so the schema largely documents accountId, before/after and actionType itself. The description reinforces responseMode's answer/evidence distinction and the 'never infer the event from a campaign title' rule, but adds little beyond what the enum descriptions already say.

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 (compares) over a specific resource (two equal-length, non-overlapping periods from one saved Meta snapshot) and enumerates outputs (coverage, changes, facts vs unknowns). It does not name sibling tools like metric_compare or performance_period, so the agent must infer differentiation, but the core purpose is unambiguous.

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?

"Preferred after reading performance-diagnosis" and "Requires exact account ID and dates from the request/context; do not invent dates" give some use-context and a hard constraint, and responseMode's answer-vs-evidence rule is spelled out. There is no explicit when-not or routing to the neighbouring comparison/reporting tools, leaving real ambiguity about when this beats metric_compare or performance_period.

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