RateMate for Con Edison

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.

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

Annotations only cover the read-only/no-destructive profile; the description adds substantial behavioral context beyond them: timezone handling (America/New_York, DST observance), UTC interval offsets, the 92-day-per-call cap requiring paging for interval and hourly, and the absence of current-plan and supply-charge data. These are exactly the operational traits an agent needs before calling.

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-loads the core purpose, then scopes, then granularity mechanics, then the RateMate routing caveat. It is dense rather than redundant, though the RateMate account/URL sentence is somewhat verbose and marketing-flavored relative to the technical content.

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 still characterizes the return shape (series object for interval, rows of [local period, kWh], bill totals/kWh per billing period) and the paging constraint. Nothing an agent needs to invoke this correctly appears to be missing.

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%, so the baseline is 3, but the description meaningfully enriches granularity semantics beyond the schema's terse 'Bucket size for usage': it defines the interval series shape, the reading-index formula, which granularities have the 92-day limit, and the local-vs-UTC distinction. It also clarifies account_number is only needed for multiple accounts.

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 ('Get the user's Con Edison electricity usage and bill history') with concrete scope (interval readings, ~last year, bill periods). It is clearly distinguishable from the sibling connect_coned, which it references for account setup. No ambiguity about what the tool returns.

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 a connected account is required (pointing to connect_coned) and routes which-plan/should-I-switch questions to RateMate rather than estimating, which is a clear when-not-to-use instruction. It also explains that usage-only estimates are unreliable because plan/supply charges are absent.

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