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

Annotations already cover read-only/idempotent safety, but the description adds real behavioral detail on top: output is labelled per Location, unreachable Locations are reported as skipped, and IDs belong to a single Location so the Location must be passed when filtering by one. That is exactly the kind of operational caveat annotations cannot express.

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?

Purpose, scope, and outputs are front-loaded in the first block, with parameter guidance following. The location paragraph is long and slightly repetitive ('Blank = all Locations if the connection has several, else its only Location') but every clause is actionable, so nothing is wasted enough to penalize heavily.

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 values need no explanation, and the location semantics are fully covered. However, the date range is the primary scoping mechanism for a period-based report and its behavior (format, empty-string meaning, default window) is documented nowhere, leaving a real gap for a 4-parameter tool.

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 0%, so the description carries the burden. It handles `location` thoroughly (single ID, comma-separated list, "all", and the blank-default rule), but `top_n`, `start_date`, and `end_date` get no treatment at all — no date format, no statement of what an empty date means, no meaning for top_n beyond its default.

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 verb+resource pairing ('Leasing activity by agent + inquiry source') and pins it to a concrete report (ProspectBoxScore, 21). It enumerates the exact outputs (top agents by prospects, source mix, application-rate proxy) and states the scope constraint that it is portfolio-wide and does not filter by property, which is enough to separate it from property-scoped siblings.

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 'Answers: ...' list gives the agent concrete questions this tool resolves, which is a clear usage signal. It does not name exclusions or alternatives — e.g. when to prefer lead_source_summary or analyze_lost_prospects instead — so the routing is implied rather than stated.

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