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

Annotations only declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the description carries real weight here. It discloses the asynchronous multi-step flow, the out-of-band email/Allow step the user must complete, the polling cadence for DATA_LOADING, and that ERROR messages should be relayed verbatim to the user.

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 imperative 'Call this first', then a compact status-to-action mapping. Every sentence earns its place: no restating of the name, no filler, and the scope caveat is placed last where it belongs.

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 no output schema, the description fully specifies the return surface by enumerating all five statuses and their meanings, plus the required follow-up for each. An agent has everything needed to drive the connection state machine to completion.

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 already documents both parameters, so baseline is 3. The description adds workflow-level meaning the schema cannot: account_number is supplied only on the second call after AUTHORIZATION_REQUIRED, which clarifies the conditional two-step invocation.

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 (connect the user's Con Edison electricity account) plus a second mode (check on a connection in progress), and explicitly bounds scope to Con Edison NYC/Westchester. It distinguishes itself from the sibling by directing the agent to get_coned_data only once status is READY.

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?

Explicitly says 'Call this first', maps every possible status to a next action (ask for account number, tell user to click Allow, retry in a few minutes, switch to get_coned_data, relay error), and states the exclusion 'Con Edison only — other utilities are not supported.' Nothing is left to inference.

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