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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds genuinely new behavior: a per-tenant catalog snapshot cache with instant reads versus a live RM API call that can be forced via live=True. That latency/caching distinction is not derivable from any structured field.

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?

Three short sentences, zero filler, and the core purpose plus returned fields are front-loaded before the caching detail and the live override. Every sentence adds information an agent needs to call the tool correctly.

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 format needn't be described, and the catalog/live split is fully covered. The remaining gap is the downstream relationship to run_report — the description implies IDs are the payload but never says these IDs feed run_report, which is the primary reason an agent would call this.

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% and the single parameter has no description of its own, so the description carries the full burden and does: live=True bypasses the catalog and hits the live RM API, live=False/default reads the snapshot. The semantics and the trade-off are both explained.

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 and resource ('List all available Rent Manager reports') plus the returned fields (IDs and names), which cleanly separates it from run_report (executes a report) and refresh_reports_catalog (updates the catalog). An agent can pick this out of a sibling list dominated by analyze_* and get_* tools without opening a 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?

Explicitly states when to set live=True: after RM admins add new ReportWriter reports, because the default path reads a cached catalog snapshot. What's missing is an explicit routing statement to the named alternatives (run_report to execute, refresh_reports_catalog to rebuild the snapshot), so the 'when not to use' half is left implicit.

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