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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond the annotations: the 5000-record cap, the truncation behavior with `truncated: true`, the meaning of `count`, and the scoping constraint ('Scoped to a site you own'). It does not describe the exact response shape, but with no output schema and the annotations covering safety, the description carries a substantial share of the behavioral burden and does it well.

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?

The description is compact and front-loaded: the core action and limit come first, then the truncation/count semantics, then the sibling comparison, then the use case and scope. Every sentence earns its place, and there is no repetition of schema or annotation content.

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 read-only export tool with 3 parameters, 100% schema coverage, and annotations covering safety, the description is complete. It explains the limit, the truncation signal, the count semantics, the alternative tool, the intended use case, and the ownership scope. An agent has everything it needs to decide when to call this tool and what to expect from the result.

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 100%, so the schema already documents all three parameters. The description adds meaning by explaining the relationship between `count` and `truncated`, and by clarifying the workspace_id semantics ('Required on a write when the connection reaches more than one workspace'). It doesn't add per-parameter syntax details, but the schema already covers the basics, and the description's extra context about the result fields is genuinely useful.

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?

The description states a specific verb ('Export'), a resource ('the records in a collection'), and a concrete limit (5000). It also distinguishes itself from query_site_records by naming the sibling and the key difference (200-record cap, no paging). An agent can tell exactly what this tool does and how it differs from the closest alternative.

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 description explicitly says when to use this tool ('Use for backup or analysis') and contrasts it with query_site_records, which 'reads at most 200 records and cannot page past them, so it can never total a collection.' This gives the agent a clear decision rule: choose export_site_data when a full collection or a total count is needed, and query_site_records when only a small read is needed.

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