get_safety

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

No annotations are provided at all, so the description carries the full burden of behavioral disclosure. The description states the metric and unit (violent crime rate per 1,000 residents), which is useful, but it does not disclose what happens for unknown towns, whether the data is recent, whether it includes other crime types beyond violent crime, or the reliability/source of figures. For a data-query tool with zero annotation coverage, the behavioral context is thin.

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?

One crisp sentence, front-loaded with the action and resource, then the unit detail. Zero waste, all content earns its place. This is an example of effective conciseness.

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?

Given the tool's simplicity (one parameter, no output schema, no nested objects), the description is fairly complete for the core purpose. However, with no annotations and no output schema, the agent gets no information about response format, error handling for invalid towns, or data vintage. For a simple tool the bar is lower, but the absence of any behavior-disclosure given zero annotation coverage leaves it at 'adequate but with gaps'.

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 0%, and the only parameter (town) has no description. Both the description and schema leave 'town' interpretation entirely to the agent. However, the description clarifies that the result is per-1000-residents violent crime rate, which adds meaning about the tool's output framing. Since there is only one obvious parameter whose semantics are inferable from the tool name and description, the gap is minimal — but a note on town name format would help.

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 uses a specific verb+resource ('Get crime figures for one town') and the scope is clear — it provides a specific metric (violent crime rate per 1,000 residents). It distinguishes from siblings by focusing on safety/crime data for a town, though it doesn't explicitly contrast with get_schools, get_housing, etc. The resource and metric are clear but the sibling differentiation is implicit rather than explicit.

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?

The description implies usage (query crime figures for a single town), but doesn't state when to use this vs alternatives, nor does it mention limitations like 'only handles one town at a time' or exclude scenarios. It doesn't say when NOT to use it or point to a sibling for related data. The context signal of a single required 'town' parameter makes usage somewhat self-evident, but explicit guidance on vs-alternatives is absent.

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