sync_account

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavior beyond them: the underlying POST /v1/sync/full call with no body on every page, and the fact that read refreshes within 60 seconds reuse the last complete snapshot. The cache-window detail is the kind of operational trait 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?

Front-loaded with the core action, then the endpoint mechanics, then the sibling pointers — a sound ordering with no filler. The capitalized 'NO body' is a stylistic quirk but does carry an instruction.

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 an output schema present, the description needn't detail return values, and it still names 'counts and cache metadata'. Combined with sibling routing and cache semantics it is largely complete; the undocumented refresh parameter is the one remaining gap.

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 0% and the single 'refresh' parameter is never named or explained in the description. The 60-second snapshot-reuse sentence only indirectly implies what refresh toggles, so an agent must guess whether refresh=false forces cache use.

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 and resource ('Download all account pages'), plus the scope constraint 'without submitting changes' and the return payload ('counts and cache metadata'). It explicitly disambiguates from apply_changes and get_account_records, so an agent can pick it without opening another 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?

The negation ('Not the apply_changes tool') and the pointer that get_account_records exposes individual record categories after the download give clear routing context. What's missing is a positive statement of when to prefer this over the sibling wait_for_sync, which also appears in the tool list.

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