get_status

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 behavioral context beyond them: passive mode makes no upstream calls, probe hits every market-data source once (implying latency), and accounts performs live per-account checks. The outstanding gap is any note on failure handling or how long a probe takes.

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?

A one-line purpose followed by per-mode definitions, front-loaded and free of filler. The help-topic list is somewhat dense inline but every clause maps to an enum value an agent must choose between.

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?

An output schema exists, so return-value shape need not be described, and mode/topic semantics are fully covered. The only omission is what detail_level changes, which matters since a caller can select it.

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%, so the description carries the full burden and mostly does: all four mode values are explained and the help-topic vocabulary is enumerated in full. The third parameter, detail_level (summary/full), is not mentioned anywhere, leaving one enum undocumented in both schema and description.

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 opens with a specific verb+resource framing ('Connector status') and enumerates the four distinct payloads the tool can return (cached health, live probes, accounts, usage guide). It is clear this is a diagnostics tool, implicitly distinct from the data-fetching siblings, though it never names a sibling to draw that boundary explicitly.

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?

Each mode is given a use-defining behavior: passive = cached only, no upstream calls; probe = one call per source; accounts = lists and live-checks each broker account; help = usage guide. This effectively tells an agent which mode to pick and what the cost tradeoff is. It does not state when to call this tool at all versus the sibling tools, which keeps it from a 5.

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