Export CDRs as CSV

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description adds substantial context beyond them: async polling capped at 45s, the 500,000-row limit with TRUNCATED marker, signed URL valid 24h, the explicit 'never returns CSV text' behavior, job_id resume semantics where filters are ignored, and a complete error-code list. Nothing contradicts the 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?

Dense but every sentence earns its place: purpose first, then behavioral constraints, then routing guidance, then polling/job_id mechanics and errors. The 'hand the URL to the user rather than trying to read it' instruction is a high-value anti-misuse note, and the error enumeration discloses failure modes without redundancy.

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 an async tool with no output schema, the description covers everything an agent needs: the return shape (signed URL, not CSV text), the failure modes (error codes), retry/resume semantics (job_id), limits (500k rows), and timeout behavior (45s poll). The only minor tension is 'for a date range' versus zero required parameters, but the schema documents the date fields, so nothing critical is missing.

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 baseline of 3 applies — the schema already documents all 8 parameters thoroughly. The description reinforces the job_id resume semantics ('filters are ignored then') and implies date-range usage, but adds no per-parameter meaning beyond what the schema provides, which is acceptable at this coverage level.

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 opens with a specific verb+resource combination ('Start an asynchronous CSV export of call detail records for a date range and wait for the download link') that precisely states what the tool does. It also explicitly names the sibling tools it is not — cdr_get_details / cdr_get_statistics — so an agent can differentiate it without opening any other 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?

The description gives an explicit usage rule: 'Use only when the user explicitly wants a file; for browsing or analysis use cdr_get_details / cdr_get_statistics.' This is a clear when-to-use/when-not-to-use statement with named alternatives, leaving nothing to inference.

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