gdex_connect

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

Annotations declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true, so the write/network profile is partially covered. The description adds meaningful context beyond that: it discloses the return payload (accountRef plus public addresses), explains that the credential stays local rather than in the conversation, and implies a persistent credential store. It does not describe failure modes or whether connectivity to the exchange is required at connect time.

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?

Three sentences, zero filler; the security constraint and the three modes are front-loaded before the downstream routing advice. The long middle sentence is dense with necessary branching detail rather than padding.

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, but the description compensates by stating what is returned (accountRef plus public addresses) and how to use it downstream. For a connection/auth tool with full annotation coverage and full schema coverage, nothing an agent needs in order 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 baseline is 3. The description goes beyond the schema by tying each parameter to a mutually exclusive intent (keyFile = sign in, create:true = make a new unfunded local wallet, accountRef = refresh an existing session) and by clarifying that accountRef is the token forwarded to all downstream trading tools.

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 (connect a GDEX trading account) and immediately names the three distinct modes of operation, which is enough for an agent to distinguish it from sibling auth tools such as auth_login, managed_sign_in, or generate_session_keypair. The security framing ('without putting any secret in the conversation') further separates it from tools that handle raw keys.

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 clear when-to-use guidance per parameter branch (keyFile to sign in from a key file, create:true for a new local wallet, accountRef to refresh) plus the routing rule that accountRef should be passed to any trading tool instead of sessionPrivateKey/privateKey. It also states a hard negative ('Never ask the user to paste a private key or seed phrase'). It stops short of explicitly contrasting against sibling connection tools like gdex_accounts or gdex_status.

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