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

Annotations cover only the safety profile (readOnly=false, idempotent=true, destructive=false), while the description adds genuinely new behavior: the browser hand-off, that the member approves there, that no password or key transits the chat, and that refresh implies a retry. These are the operational facts an agent needs for an auth flow and they are not derivable from 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 correctly: purpose, then triggers, then the flow, then mode semantics. It is slightly redundant in re-stating the three mode descriptions that already live verbatim in the schema, which is the only reason it isn't a 5.

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 1-parameter, zero-required mutation tool with no output schema, the description is nearly complete: flow, triggers, mode effects and post-refresh retry are all present. It stops short of describing what success or failure looks like to the caller (e.g., whether the connection is then active for subsequent calls), which it could state since no output schema exists.

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% and the enum description already restates each mode, so the baseline is 3. The description adds a small amount beyond the schema — 'connect (the default) starts sign-in when the connection needs it' and the retry instruction for refresh — which is meaningful but largely overlaps the enum text.

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 states a specific verb and resource ('Connect this assistant to the member's own FirmLedger account by sign-in (OAuth), or renew or replace that connection') and scopes it against siblings like revoke_connection and connection_status by naming the three modes. An agent can distinguish this from the status/revoke siblings without opening any schema.

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 gives explicit trigger phrases ('connect me to my account', 'sign me in', 'switch accounts') plus a per-mode selection rule: connect when the connection needs it, reauthenticate to end the current connection and re-choose an account, refresh for an about-to-expire token followed by a retry. That is when-to-use and which-alternative guidance in one place.

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