account_refresh

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

Annotations declare a non-readonly, non-idempotent, open-world call; the description earns credit by explaining why — credentials may rotate, and repeat calls within 24h degrade to verification only. The unresolved gap is the return value, since no output schema exists to say what a rotated credential response looks like.

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?

Four terse sentences, each adding a distinct constraint (no SMS/purchase, credential rotation, 24h behavior, checkout exclusion) with the core purpose front-loaded. The semicolon-joined middle sentence compresses two separate behaviors less cleanly than separate statements would.

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?

Behavioral caveats are well covered for a mutation tool, but with no output schema the description should say what comes back on success (new token? status only?) and what "unknown outcome" looks like to the caller. The "account" parameter also goes uncharacterized, leaving the definition workable but incomplete.

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?

The single parameter "account" has 0% schema description coverage, so the description carries the full burden — yet it never says whether this is an account ID, email, or username, nor what format is expected. This is a meaningful gap for the only required input.

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?

"Maintain an existing session" plus "may rotate credentials" conveys a session/credential refresh action, which is specific enough to tell apart from account_check or account_connection_instructions. It stops short of naming the resource type explicitly (account/session for what service), leaving a little ambiguity.

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?

"without SMS or purchases" and "an unknown refresh outcome requires local login" give clear conditions and a fallback path, and "Does not renew checkout runtime" rules out an adjacent use case. However, no sibling is named, so an agent must still infer why it would pick this over account_check.

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