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

Annotations already declare readOnly/idempotent/non-destructive, so the description's added value is the multi-Location execution semantics: per-Location labelled output and unreachable Locations reported as skipped. That is genuine beyond-schema behavior. It does not discuss cost, truncation of the leaderboard beyond top_n, or what 'ranked by severity' means numerically.

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 purpose and metric inventory before parameter detail, which is the right order for an agent scanning definitions. The example-question list and the location paragraph are both useful, though the location block is dense and slightly repetitive about multi-Location defaulting.

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?

An output schema exists, so return-shape explanation is not required, and the scope/ranking description plus Location semantics cover the core. However, with 0% schema coverage, leaving the date range, portfolio, and property_ids parameters entirely unaddressed means an agent cannot know how to scope the analysis period without guessing.

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%, so the description must carry the full burden, yet it explains only 'location' in depth. Five parameters, including top_n, start_date, end_date, portfolio and property_ids, are never mentioned, and the date-window parameters matter a lot for an inspection-period analysis. Substantial documentation gap for a 6-parameter tool.

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?

Opens with a specific domain statement (InspectionActivity, 273) and then enumerates exactly what is computed: per-property counts, open vs closed, action/severe/review-needed totals, severity ranking, worst inspections, and an inspector leaderboard. The sample questions ('which properties have open inspections', 'how many inspections happened this quarter') make it distinguishable from neighbors like analyze_service_issues or get_work_orders.

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 example questions give clear situational context for when to reach for this tool, and the location paragraph explains multi-location defaulting plus the rule that filtering by a property/tenant ID requires passing the owning Location. It stops short of naming alternatives or exclusions (e.g. when to prefer analyze_service_issues over this), so it is clear context without explicit routing.

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