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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the bar is lower. The description usefully discloses the audit's data scope across seven domains, but says nothing about what the agent receives back — per-project counts, a pass/fail verdict, or flagged discrepancies — which matters for a tool with no output schema.

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, the audit scope front-loaded and the trigger conditions second. Every clause carries information; nothing is repeated from the title or annotations.

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?

For a zero-parameter, read-only check with no output schema, the description covers purpose, scope, and timing. The main remaining gap is the shape of the result, since no structured output definition exists to fill that in.

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?

The tool takes zero parameters, so there is no parameter semantics to explain; baseline 4 applies. Nothing in the description misleadingly implies inputs exist.

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 pair (counts / checks) and the resource (projects), then enumerates the seven entity types being counted. No sibling tool performs cross-project isolation auditing, and the description makes that distinction obvious versus the various list_* tools.

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 two concrete triggers: after adding a project, and whenever data looks misplaced. That is clear contextual guidance. It stops short of naming an alternative or exclusion (e.g., use list_knowledge for a plain listing), so it is not a full when/when-not statement.

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