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

Annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false) only give the safety profile; the description adds that it performs a real sign-in, never stores or returns tokens, enumerates concrete failure reasons with fixes, and describes the evidence returned. This is substantial context beyond the structured fields and is consistent with the 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?

Front-loaded with the core purpose and efficient throughout, but it is a dense single paragraph packing return values, failure modes, and alternatives. Every sentence earns its place, though slightly heavy.

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 fully carries the return-value burden, explaining the `verified` result, the evidence fields, and the `failure`/`fix` structure on failure. Nothing needed 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 coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema by tying email/password to credentials from create_test_user and clarifying that origin must be an allowed origin. It doesn't add much syntax detail, so a 4 rather than 5.

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 ('Prove a sign-in works end to end') and elaborates the exact mechanism (signs in through the Bridge environment as the SDK does, exchanges session for tokens, verifies against JWKS). This clearly separates it from read-only siblings like get_auth_config or debug_auth_issue.

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?

Gives concrete when-to-use ('Use the credentials from create_test_user') and an explicit alternative path for the contrasting scenario ('If sign-in works here but not in the app... call get_integration_guide with topic=auth'). Both the precondition and the fallback tool are named.

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