Create Principal Disclosure

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

The description and tool name both assert a 'create' operation, but the annotations declare readOnlyHint=true and destructiveHint=false. That is the same contradiction pattern as a 'creates a record' description paired with readOnlyHint=true. If this is actually a pure derivation that returns a filtered view, the description must say so instead of implying a new resource is persisted.

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 short sentences, front-loaded with the action, with no filler. The second sentence is largely a restatement of 'selective disclosure', so it earns its place only marginally, but the overall length is appropriate.

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?

There is no output schema, so the description should explain what a disclosure actually is and what the caller receives (a document, a token, a presentation, a stored record). Combined with the unresolved readOnly contradiction and no stated lifecycle, an agent cannot confidently predict the side effects or return of this call.

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?

There is a single parameter with 100% schema description coverage, and the enum values (public / verified-only / minimal) are already fully explained in the schema, so the description does not need to restate them. Baseline 3 is correct: the description adds no semantic value about the level parameter beyond what the schema provides.

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 gives a specific verb+resource ('Create a selective disclosure of principal identity') and a one-line scope note about controlling revealed information, so the operation is unambiguous on its own. It does not, however, differentiate itself from nearby identity tools such as identify, create_principal, or add_principal_report, leaving the agent to guess which identity operation applies.

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 create a disclosure versus using identify or create_principal, nor any prerequisites (does a principal already need to exist? does this need a key?). 'Controls how much info is revealed' hints at the purpose but stops short of any when-to-use or when-not-to-use rule.

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