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

The annotation readOnlyHint already marks this as safe to read, and the description reinforces that by starting with 'Read'. It adds behavioral context by naming exactly which data domains the read covers, giving the agent a clearer picture of what the call will fetch beyond the bare annotation.

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 entire description is a single front-loaded sentence starting with the key verb 'Read'. It lists the relevant data categories in a compact, scannable way with no filler or redundancy.

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 simple read-only tool with an output schema and a readOnlyHint annotation, the description is nearly complete. The only meaningful gap is the lack of prose around the parameters, especially tenant_id, but the required audit_project_id is still discoverable from the schema.

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%, and the description does not explain audit_project_id or tenant_id. The term 'audit_project_id' is somewhat inferable from the tool purpose, but tenant_id is left entirely unexplained, so the description fails to compensate for the lack of schema parameter details.

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 uses the explicit verb 'Read' and identifies a specific resource ('AI Stack Audit project state') plus concrete data categories (deliverable refs, credit ledger, Desk/CRM links). This clearly distinguishes it from sibling tools like artifact_audit or other status 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?

The description implies when to use the tool: whenever an agent needs to read the AI Stack Audit project state or its related data. However, it offers no explicit guidance about alternatives, when not to use it, or how it compares to other status-oriented sibling tools.

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