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

Annotations (readOnlyHint, openWorldHint, idempotentHint) indicate safe, non-destructive behavior. The description adds significant context: the tool returns a runbook to execute step-by-step, not final results. It also includes a detailed 'Data accuracy contract' setting strict expectations about not inventing data and requiring calculations to be labeled. No contradiction with 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?

The description is moderately long but well-structured: it opens with the core purpose, then usage conditions, then behavioral notes (runbook nature, data contract). It is front-loaded with essential information. The data contract section adds length but is valuable for agent behavior. Slightly longer than ideal but each sentence earns its place.

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 no output schema, the description compensates fully: it explains the output (runbook/skill_body with steps), the required connectors, and the expected workflow. It also covers input, process, and behavioral constraints. The detailed data contract further ensures the agent knows how to handle results. This is a complete specification.

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?

The input schema has only one optional parameter ('user_question') with a clear description. Schema coverage is 100%, so baseline is 3. The description does not add further detail about the parameter beyond what the schema already provides, so no improvement is warranted.

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 states the tool's primary action: 'Build a structured 14-day cash-recovery plan'. It specifies the resources involved (overdue invoices, email threads, contract terms from Drive) and the output (prioritized collections sequence with drafted follow-ups). It also distinguishes itself from siblings by being a cash-recovery-specific tool among many other 'featured_*' skills.

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 lists when to use the tool ('Use when the user asks how to collect overdue invoices, recover cash, chase receivables, 'who owes me money', or improve AR / collections'). It also clarifies that this is a CorpusIQ Skill returning a runbook, not a final answer, and instructs the agent on how to proceed and end the response.

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