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

Annotations already cover the safety profile (readOnly, non-destructive, open-world), so the description's job is to add context, and it does: it discloses what the card contains (counts, cost per action, value, overall plus per campaign) and flags that the purchase event matching Ads Manager is highlighted, which is real reconciliation guidance. It says nothing about date defaults, pagination or row limits, which keeps it short of a 5.

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?

Two sentences, front-loaded with the payload and then the usage cue, with no filler. The event enumeration is a little long but earns its place by telling the agent what categories will appear.

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 has to convey what comes back, and it does at a high level (overall and per-campaign counts, cost per action, value). An 8-parameter tool with zero required parameters could say more about defaults, such as which date range applies when dates are omitted, but nothing essential for calling it is missing.

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 50%: the ambiguous parameters (detail with its summary/full semantics, account optionality, folder, language) are already documented in the schema, and the description adds no parameter guidance of its own. The undocumented ones (campaign, start_date, end_date, date_range) are largely self-describing, so the schema carries the load and 3 is the appropriate baseline.

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 names a specific resource and scope: every conversion/action Meta recorded (purchases, leads, add to cart, messages, registrations, link clicks) with counts, cost per action and value, overall and per campaign. That is far more concrete than the bare name. It does not, however, differentiate itself by name from close siblings such as meta_performance, meta_insights_query or meta_tracking_audit.

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 gives one usage cue, 'Use when the user asks exactly what was tracked', which implies an event-level breakdown instead of aggregated performance. It offers no exclusions and never names an alternative, so an agent comparing this with meta_performance or google_ads_conversions must infer the boundary itself.

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