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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds real context beyond them: the hard 90-day window, that spend is expressed in the account currency, and — most valuably — that campaign rows mix Meta metrics with internal ones (received, whatsapp_sent, replied, qualified, cost_per_qualified_lead) and the formula behind cost_per_qualified_lead. It does not cover pagination or rate/limit failure behavior.

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 resource and scope, then the metric inventory. The long metric list is dense but each item carries information the agent needs since there is no output schema. Slightly list-heavy, but no filler sentences.

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 must describe the return shape, and it does so field-by-field across both Meta and internal metrics, plus the 90-day ceiling. Remaining gaps are pagination/row-limit behavior and failure modes on out-of-range dates; these are minor against the breadth of what is disclosed.

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 description coverage is 80%, which sets a baseline of 3, and the description compensates further by defining the non-obvious metrics (received = leads that reached HellouOne, qualified = hot or warm leads, cost_per_qualified_lead = spend / qualified) and by tying ad_account_id conceptually to the ad-account entity. Semantics of the 'fields' and 'level' enums are left to the 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 concrete verb+resource: 'Ad results for one ad account from Meta' with the aggregation levels (campaign, adset, ad) enumerated and a full list of the returned metrics. An agent can tell this is a per-account performance/results pull. It never names a sibling (e.g. get_facebook_marketing_overview, get_campaign) to draw the boundary explicitly, so it stops short of a 5.

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 'range of at most 90 days' constraint and the level enum imply when this tool is applicable, and the campaign-only internal metrics hint at its reporting use case. However, there is no explicit when-to-use/when-not-to-use statement and no routing to alternatives such as the marketing overview or list-level tools, so usage remains inferred.

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