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

With no annotations at all, the description carries the entire burden. It discloses that results are aggregated and grouped by category, which is the most important behavioral trait here. It says nothing about whether this is a read-only query, whether results are counts over the whole range, whether pagination or truncation applies, or what happens for a school with no data in range.

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?

A single compact sentence with the operation front-loaded and the key-provenance note last; nothing is redundant. It is dense to the point of being terse, packing the enumeration of seven grouping categories into the middle of the sentence, but every clause earns its place.

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 three-parameter read query with full schema coverage and no output schema, the description covers intent, output grouping, and key sourcing. It still leaves out the response shape (counts per group?), behavior for empty results, and any handling for oversized radii, which an agent would want before calling. Adequate but with clear 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?

With schema coverage at 100%, the documented parameters already carry their meaning, so 3 is the baseline. The description adds one item beyond the schema: the provenance of schoolKeyid. However, it adds nothing about the admissible radius values or the year range, both of which the schema already handles, and it does not say how the grouping categories relate to any parameters. Net effect is marginal.

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: querying accident hotspots within a given radius of a school, grouped by seven named categories (location, peak time, age, vehicle type, collision type, cause, yearly stats). It is clear what it returns and distinguishes itself from list_schools/get_school_rank by naming them only as sources of schoolKeyid. It never differentiates itself from get_school_accident_points or get_cbi_hotspots, even though both appear to cover nearby territory.

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 trailing clause gives the key dependency: schoolKeyid must come from list_schools or get_school_rank, which is real usage guidance for an agent that would otherwise lack it. There is no when-to-use / when-not-to-use guidance versus get_school_accident_points or get_cbi_hotspots, no prerequisites, and no statement about what a hotspot means relative to raw points.

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