ad_get_inactive_users

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

No annotations are provided, so the description carries the full burden, and it discloses almost nothing: the [READ] tag signals a non-mutating operation but is not a formal annotation. It does not say which activity signal is used (lastLogon, lastLogonTimestamp), which domain(s) are queried given there is no domain parameter, or how results are bounded. Only the presence of an output schema spares it from a 1.

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?

The definition is one front-loaded sentence plus category tags with no filler, so it is structurally sound. It is, however, under-specified rather than concise — the brevity comes at the cost of the information an agent actually needs.

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?

An output schema exists, so return values need not be described, but that is the only burden lifted. With no annotations, 0% parameter coverage, and no explanation of the inactivity criterion or domain scope, the definition is thin for a security-audit query whose correctness hinges on the `days` threshold.

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 0% across all three parameters, so the description must compensate and does not. 'Sem atividade recente' faintly implies a recency window that maps to `days`, but `days`, `limit`, and `correlation_id` are never explained — notably the default of 90 days is nowhere surfaced.

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 verb ('Identificar') and resource ('usuarios') qualified by 'sem atividade recente', which distinguishes it from siblings like ad_get_disabled_accounts and ad_get_locked_accounts that target different account states. It does not explicitly name those siblings, but the qualifier alone is enough for an agent to tell them apart.

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?

There is no statement of when to use this versus ad_list_users, ad_search_users, or ad_generate_inactive_accounts_report (the report variant), and no exclusions or prerequisites. The key ambiguity — what counts as 'recent' — is left entirely unaddressed.

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