ck_external_service

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

Annotations already set readOnlyHint=false, destructiveHint=false, idempotentHint=false, indicating this tool can create or modify data. The description adds value by mentioning auto-redaction of PII and rate limit tracking, but does not fully specify side effects of each mode or authorization 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?

The description is extremely concise—three short phrases covering purpose, features, and modes. Every sentence adds unique value without redundancy, and the core purpose is front-loaded.

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?

Given the tool's complexity (12 parameters, output schema present, nested objects), the description provides sufficient high-level context for an agent to select the correct mode and understand the tool's role. The presence of an output schema reduces the need to describe return values. A bit more detail on mode-specific prerequisites would elevate completeness.

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?

100% schema description coverage sets a baseline of 3. The description does not add parameter-level details beyond what the schema provides, though it contextually explains modes that influence parameter usage (e.g., 'limit' is relevant for top_services mode).

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 clearly defines the tool's purpose: 'Track and govern agent interactions with external SaaS APIs.' It lists specific capabilities (rate limits, cost attribution, PII redaction) and enumerates operational modes (record, summary, rate_limit_status, top_services), making it distinct from sibling tools that focus on other domains.

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 names the four modes and their purposes, guiding the agent on when to use each (e.g., 'record (log an interaction with auto-redaction)'). However, it does not provide explicit 'when not to use' guidance or compare directly to siblings like ck_cost_optimizer or ck_observability.

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