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

Annotations declare a write operation (readOnlyHint=false, idempotentHint=true, destructiveHint=false); the description adds that the write targets a per-tenant catalog file, returns a diff against the prior snapshot, and never fans out across Locations. That last constraint is genuinely useful behavioral context an agent could not infer from annotations.

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 purpose sentence, then return behavior, then the intended-timing note, then parameter guidance — a sensible order with little waste. The location paragraph is slightly verbose for one optional string but still 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?

All decision-relevant facts are present for a one-parameter mutation: what it writes, what it returns, when to call it, and the location precondition. An output schema exists, so return values needn't be further detailed, and the description already summarizes the diff shape.

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% (the single property has no description), so the description must carry the full burden and does: it explains that location is an optional single Location ID, when it becomes required, and where to find valid IDs (list_locations). It also states the tool will not fan out, closing the obvious misinterpretation.

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: snapshotting live /Reports + /ReportWriterReports into a per-tenant catalog file, plus the diff it returns. An agent can distinguish this from listing/read tools like list_reports or run_report because the snapshot-and-diff framing is explicit, though no sibling is named directly.

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?

"Intended for after RM admins add or rename reports" gives a clear triggering condition, and the location paragraph specifies when the parameter is required (multi-Location connections) and points to list_locations. No explicit when-not-to-use case, but the practical context is well covered.

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