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

Annotations already cover readOnly/idempotent/non-destructive/openWorld, so the description goes beyond them usefully: it discloses the need_input + `missing` contract, that `peaks` come back when interval rows are sent, and that Texas retail bills return no_rates rather than rates. It also states 'Free; nothing stored' and the 'never guess' input rule, which are behavioral facts not present in the 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 trigger condition ('Use this when...') followed by the call procedure and the input list, so the agent can act on the first clause. It is dense with parenthetical examples and one long run-on sentence, which costs it a point, but each sentence carries operational information rather than filler.

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?

For a 5-param, nested-schema tool with an output schema, the description covers the trigger, the partial-call workflow, the return-state signals, and the key data-handling guarantees. Nothing an agent needs in order to invoke it correctly (including that an incomplete call is acceptable) is 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 description coverage is 100%, so the baseline is 3; the description earns above-baseline credit by explaining how to populate the parameters in practice – pass `bill` or `bill_text` plus `address`, everything else is optional, and omit unstated fields rather than guessing. It does not contrast alternatives (bill vs bill_text vs usage_csv) or clarify precedence when several sources are given.

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+resource ('check' a 'business electricity bill') and enumerates the concrete jobs it performs: rate-plan comparison, cost of a coming rate change, peak kW explanation. The purpose is unambiguous even though the siblings (feedback tools) share no domain, so no sibling differentiation is needed.

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 when to use it ('when a small business wants its electricity bill checked...'), instructs the agent to 'always call scan_bill first' with whatever the user gave, and enumerates several partial-input scenarios (only total, only kWh, address alone, CSV snippet, Texas retail bill). It also names the terminal return states (need_input/missing, peaks, no_rates) so the agent knows the flow does not dead-end.

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