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

Annotations already mark it read-only and non-destructive; the description adds substantial behavioral context by disclosing the knowledge sources, citation behavior, confidence-level reporting, and handling of corpus silence. This goes well beyond the annotations and gives the agent an accurate model of what the response will contain.

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?

The description is longer than average but dense with high-value information: use cases, exclusions, jurisdiction guidance, output behavior, and an example. It is arguably slightly verbose for a tool description, but every sentence contributes; a few structuring bullets could improve scannability.

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 supplies essential return-value context: citations to a-du.homes, a confidence level, and explicit behavior when the corpus is silent. It also defines the corpus boundaries and routing to sibling tools, making the definition self-sufficient for correct invocation.

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 50%: jurisdiction has a description but question does not. The description compensates by explaining jurisdiction's role ('Name the jurisdiction when the question is about a specific city so its research is included') and providing a concrete JSON example. Question semantics are implied through the extensive use-case list, which is helpful but less formal than the jurisdiction instruction.

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 clear verb and resource: 'Answer any question about Accessory Dwelling Units from A-du's published guides...' and immediately distinguishes itself from the specific sibling tools by listing what falls outside its scope. This makes the tool's role unmistakable even before inspecting the schema.

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?

It explicitly enumerates when to use the tool (definitions, process, landlord/tenant questions, costs, anything not covered by siblings), when to prefer alternatives ('Prefer those tools when one fits; they return live data'), and how to structure city-specific questions. The guidance is direct and prescriptive.

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