Login Session

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

Annotations only flag non-read-only, non-idempotent and open-world; the description adds substantial context beyond that: the login is bound to `mcp-session-id` server-side and must not be re-passed, the signed timestamp has a server-side age limit (default 24h) with the named `SIGNATURE_EXPIRED` failure, and an internal API key may be auto-loaded as a side effect. The security guardrail ("Never ask the user for private keys or seed phrases") is exactly the kind of behavior an agent cannot infer from structured fields.

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?

Purpose and the exclusive-or choice are front-loaded in the first clause, and every following sentence adds non-redundant information (session binding, expiry behavior, security rule). The return-shape sentence partially duplicates the existing output schema, and the single dense paragraph with semicolon-separated modes is harder to scan than a short bulleted split, but there is no filler.

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 an authentication entry point with two mutually exclusive credential paths, the description covers prerequisites (get the message first), side effects (API key auto-load, session binding), failure mode (SIGNATURE_EXPIRED), and the security constraint. Although an output schema exists, it also names the returned fields, so an agent can reason about `authMode` and `unlocked` without opening the schema.

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 both params are documented there, so the baseline is 3; the description earns above that by explaining provenance and consequence — the signature must be produced by the user's wallet over the `message` returned by `tronsave_get_sign_message`, and each param unlocks a distinct tool set. The exclusive-or requirement is stated in both places, so that part is redundant, but the meaning of each credential is genuinely enriched.

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?

Opens with a specific verb and resource ("Log in to TronSave") plus the crucial scope qualifier "for the rest of this MCP connection", which immediately separates it from per-call auth tools and from siblings like `tronsave_logout` and `tronsave_get_session_status`. The two auth modes are named with their concrete effects, so the agent knows exactly what the call accomplishes.

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 explicit routing between the two modes — `signature` unlocks wallet tools, `apiKey` unlocks internal-account tools — and names the prerequisite sibling `tronsave_get_sign_message` as the source of the message to sign. It does not state what to do if a session already exists (e.g., check `tronsave_get_session_status` before logging in, or that a repeat login replaces the session), which is the one routing gap.

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