Export bounded private testimonials

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

Annotations declare destructive=true / readOnly=false / openWorld=true, and the description goes well beyond them with concrete file behavior: exclusive new 0600 file, no overwriting, no media download, no URL following, no retries, and the explicit warning that this is not an atomic complete backup. That is exactly the extra context a mutating export needs.

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?

Two short sentences, front-loaded with the core action and then the guardrails; nothing is padded. The telegraphic phrasing ('new0600') costs a little clarity for the sake of brevity.

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 17-parameter destructive export with no output schema, the description covers the highest-risk behaviors (no overwrite, non-atomic, no retry) that annotations alone would not convey. It leaves the return shape and the receipt/offset mechanics unstated, which is a minor gap.

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 59%, so the schema already documents lang, sort, limit, query, account, output_file, max_items, max_pages, and start_offset. The description reinforces the pagination/cap semantics ('short native page', 'local caps') that relate to page/limit/max_items/max_pages, but adds no syntax or constraints for the undocumented params (type, order, rating, approved, integration).

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+resource with scope: a 'confirmed paginated GET export' of testimonials into a new JSON file. This distinguishes it from list_testimonials and the other read siblings. It falls short of 5 only because the dense jargon ('new0600') makes the object of the export slightly opaque on first read.

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?

Usage is implied rather than stated: 'Stop on short native page or local caps' and 'implies an atomic complete backup' tell the agent this is a bounded, non-backup export, and the confirm param's schema note gates invocation. But no alternative sibling is named and no explicit when-not condition is given.

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