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

Annotations already cover the safety profile (readOnly, idempotent, openWorld), and the description still adds real behavior: the response includes a provenance date ('the date Kolmo read it'), auto-derivation of utility/city/yearBuilt from an address, and a 'check' line that reports a still-missing fact. This is meaningful context an agent could not infer. It does not discuss caching, rate limits, or coverage limits of the rebate list.

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?

Three compact sentences: the first front-loads scope and return content, the second explains address derivation, the third explains the 'check' line. Dense but every sentence carries information, though the phrasing ('what each pays, who must install it') is slightly compressed at the cost of easy scanning.

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 an 11-parameter tool, the description covers the required input path (work), the address-vs-city fallback, and the ask-back loop via the 'check' line, and an output schema exists so return structure need not be restated. The main gap is that several financial inputs (income, household size, project cost) are never explained even contextually.

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 only 36%, so about half the parameters (annualIncome, householdSize, projectCostUsd, yearBuilt, heating, work) carry no description in either place. The description compensates for the address/city relationship and hints at the `confirmed` loop via the 'check' line, but leaves the income, cost, and heating inputs unexplained. Partial compensation only.

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 names the exact verb (find rebates) and resource, scopes it geographically and by program (PSE, Seattle City Light, Seattle Clean Heat, HomeWise, WA HEAR), and enumerates the return payload (payout, installer requirements, post-rebate price, source page). This clearly separates it from siblings like get_financing_options or get_project_roi.

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?

Usage context is clear: it operates on a specific job with a required `work` list, and the address/city branch is explained ('An address fills in utility, city and year built', city 'when there is no address'). There is no explicit when-not-to-use or named alternative, so it falls short of a 5.

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