Export bounded private testimonials

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

Annotations already declare readOnly=false, destructive=true, openWorld=true, idempotent=false, but the description goes well beyond them: exclusive file creation with 0600 permissions, no overwriting, no media/URL fetching, no retries, and an explicit warning that the result is not an atomic complete backup. These are exactly the behavioral traits an agent needs before calling a file-writing export.

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 tight sentences with the core action front-loaded and zero filler. It is occasionally over-compressed (bare '0600', 'native page', 'local caps') in a way that costs a little readability, but nothing is wasted.

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?

No output schema exists and there are 17 parameters, so the description carries substantial burden. It thoroughly covers the behavioral envelope and failure/stop semantics, but leaves the confirmation workflow, account/integration scoping, and the shape of the resulting file largely unexplained.

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 only 59% across 17 parameters, so the description must carry weight. It alludes conceptually to confirm ('Confirmed'), the local caps (max_items/max_pages), and page size ('short native page'), but never clarifies undocumented fields such as approved, account, integration, or start_offset behavior. Partial compensation, not full.

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 concrete verb+resource+artifact: a paginated GET export of testimonials written to an exclusive new 0600 JSON file. An agent can immediately distinguish this from list_testimonials or preview_testimonial_batch. It stops short of naming a sibling to avoid, which keeps it from a 5.

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?

Gives operational guidance on when to stop (short native page or local caps) and a list of non-goals (no media download, no URL following, no retries, no atomic backup), which implicitly scopes the tool. However it never states when to prefer this over list_testimonials, preview_testimonial_batch, or submit_testimonial_batch, nor the prerequisites implied by 'Confirmed'.

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