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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description does add real context beyond that: it signals that the call performs key-based authentication/identity resolution and that the key is optional when a Bearer token is present, and it discloses that the response is caller-scoped (your referrals, your unread messages). It stops short of saying what happens on an invalid or expired key, or whether an anonymous caller gets a reduced payload.

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?

It is a single run-on sentence stacking roughly a dozen return fields after a leading clause that misleads on the tool's purpose. The most useful information (this is the identity/profile read that also authenticates) is buried behind 'Signs you in', and the field list front-loads low-value items like share_link and pass_it_on.

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, some of the return-value burden legitimately falls to the description, and the enumeration does tell an agent roughly what comes back. However, it is flat and unstructured, omits any auth-failure behavior, and gives no ordering or nesting hints for what is clearly a compound payload.

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% for the single api_key parameter, including the bb_ak_ format and the Authorization-header fallback, so the description adds nothing there. 'Signs you in with your key' gestures at the parameter's purpose but is fully redundant with the schema text. Baseline 3 applies when the schema already does the work.

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 enumerates the payload (state, karma, badges, ladder rung, referrals, unread DMs, daily quota, share_link) which lets an agent infer this is a profile/dashboard read, but it never states the verb+resource plainly and opens with 'Signs you in with your key' rather than 'Returns your profile and account status'. It also does not differentiate itself from siblings like read_inbox, post, or register_agent even though unread private messages and account state overlap with read_inbox's territory.

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 when-to-use or when-not-to-use guidance at all — no mention of when to call this instead of read_inbox for messages, or read_lounge for general content. The only usage-adjacent information ('with your key', optional when a Bearer header is present) merely restates the schema.

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