emu_export_cdr_csv

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

No annotations provided, so the description carries full responsibility. It fails to disclose the output size expectations or file format details (e.g., CSV headers, delimiter, encoding), whether it writes to a file or returns a string, or if it has a limit on rows despite the input schema having a 'limit' param. It doesn't reveal any side effects (e.g., it does not consume/delete the projections — 'export' implies read, but that's unconfirmed).

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?

Single tight phrase, no fluff, front-loads the action 'Export'. It earns its position. Slight ding: lacks the standard 'Use this when...' pattern that would improve usage guidance, but as pure conciseness it's strong.

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 tool with 2 completely undocumented params, no annotations, and no output schema, this is insufficient. The agent needs to know the meaning of 'canonical CDR projections' (likely published via emu_publish_cdr), the expected CSV structure, and whether sessionId filters a particular export batch. Without that, an agent is guessing. Sibling context doesn't fully disambiguate.

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?

Both parameters (limit, sessionId) are completely undocumented in the schema (0% coverage), and the description provides no context for either. The agent cannot know what 'limit' limits (number of rows? file size?) or what sessionId refers to (a CDR generation session? a call session?). The description adds nothing about params; with 0% schema coverage it needed to compensate heavily and doesn't.

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 verb+resource+format: 'Export canonical CDR projections as Cisco-style CSV'. 'Canonical CDR projections' implies the already-published/normalized call detail records, distinguishing it from raw emu_generate_cdrs or emu_publish_cdr. It's clear enough, though it only differentiates from siblings implicitly.

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?

No guidance on when to use this vs. siblings like emu_list_cdr_records, emu_get_cdr_publisher, or emu_export_snapshot. It doesn't state prerequisites (e.g., must publish CDRs first) or whether 'canonical projections' refers to Publisher processed records rather than generated raw CDRs. Agent must infer from the name and 'canonical' hint.

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