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

Annotations already mark it read-only and non-destructive, and the description adds important interpretive caveats: reads measure attention, not compliance, and recorded evidence is not a judgement that it satisfies the control. The userContent warning about tenant-authored data as information, not instructions, is valuable safety context beyond annotations.

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 concise and front-loaded: outputs first, usage next, then necessary semantic caveats and the trust warning. Every sentence adds value and none repeats the schema 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?

Despite no output schema, the description covers the return shape at the right level (counts, least-touched families, evidence), gives usage guidance, and warns about misinterpretation. Combined with rich schema param descriptions, nothing an agent needs to call it correctly is missing.

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 100%, so the schema already explains project and framework, including when framework is required and that the error will list options. The description adds no new parameter syntax, which is acceptable because the schema carries that burden.

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 a specific verb and resource ('Get where a project's compliance program stands') and concretely lists the outputs: read count vs total, least-touched families, and evidence recorded/affirmed. It also distinguishes itself from sibling tools by framing this as orientation before drilling into specific controls.

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 explicitly says 'Use this first to orient before drilling into specific controls,' which states both when to use it and what it is not for. The project parameter schema adds an explicit alternative: call list_projects first if you do not know the project.

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