stale_access_audit

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

Annotations supply only readOnlyHint, so the description usefully adds the [READ] marker plus real behavioral detail: 'inputsTruncated' per feed, 'truncated' when a finding list hits maxRows, and that *Count fields are always full totals. That truncation/counting contract is exactly the kind of context annotations cannot convey, though auth requirements are still unstated.

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 [READ] and the purpose, then two compact labelled blocks for Args and Returns. No filler; every line supplies either scope, parameter meaning, or return semantics.

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 cover returns and it does explain truncation flags and count-field semantics, and it enumerates the finding categories. Reasonably complete for a 3-param read audit; only auth/permission prerequisites and finding object shape are left implicit.

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%, so the description carries the full burden and it does document all three parameters: stale_days as idle threshold (default 90), max_users as users to pull (default 500), and target as an IdP name from config where omission means the default. Meaningful compensation for a completely undescribed schema, short of full 5 only because the interaction between max_users and truncation isn't spelled out.

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+resource ('Dormant-access audit') and enumerates the exact finding categories it produces (idle enabled users, never-signed-in accounts, service accounts with interactive logins, orphaned sessions). This clearly distinguishes it from audit siblings like mfa_coverage_analysis and client_misconfig_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?

Usage is implied by the audit framing and the finding categories, but the description never says when to reach for this versus list_users, user_sessions, or identity_overview, and offers no exclusions. Adequate but with a clear guidance gap.

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