ad_generate_inactive_accounts_report

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

No annotations are provided, so the description carries the full behavioral burden, and it supplies almost nothing. The '[READ]' marker hints at a non-destructive operation and the '[Reports, Inventory & Automation]' tag hints at a reporting category, but there is no disclosure of output size, aggregation scope, permissions required, or performance characteristics of a directory-wide scan. For a report-generation tool with zero annotation coverage, this is a substantial gap.

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 description is short, but it is underspecified rather than concise: a category tag plus a three-word Portuguese fragment. The bracketed metadata occupies most of the text while conveying little operational meaning, and nothing useful is front-loaded about scope or output.

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 the rest of the picture is missing: undefined parameter semantics, no usage context, no behavioral traits, and no differentiation from siblings. For a reporting tool over a directory, an agent cannot confidently decide when to call it or how to set 'days'.

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 three parameters, and the description explains none of them. The 'days' threshold (default 90) is the single most consequential input for defining 'inactive', and neither the schema nor the description clarifies whether it is a lookback window or a last-logon cutoff. 'output_format' and 'correlation_id' are likewise undocumented.

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 phrase 'Relatorio de contas inativas' (inactive accounts report) identifies the resource and the reporting action, so an agent can roughly infer it produces a report about inactive accounts. However, it is a bare noun phrase in Portuguese with no verb, and it does not distinguish itself from the closely related sibling ad_get_inactive_users or ad_get_stale_computers, which also surface inactivity data. Purpose is inferable but not clearly delineated.

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 guidance on when to use this tool versus ad_get_inactive_users (list) or ad_generate_user_report (report). The '[READ]' tag implies a non-mutating operation but says nothing about context, prerequisites, or exclusions. The agent is left to guess from the name alone.

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