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

With no annotations, the description fully discloses behavior: input format (raw CSV text from QBO Reports → Accountant → Journal), limits (max 5,000 rows, 5 MB), output (flagged lines with severity and a shareable URL), and what the tool does not do (paid product features). No contradictions.

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 well-structured and front-loaded with the core purpose. Every sentence adds value—input details, use cases, limitations, and relation to paid features. No redundant or wasted words.

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 complexity of anomaly detection and absence of an output schema, the description is remarkably complete. It covers input, output, use cases, limits, severity levels, and ties to the product roadmap, leaving no critical gaps for an AI agent.

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 baseline is 3. The description adds context beyond the schema by explaining the expected CSV format and the purpose of the optional fileName as a label. This extra information raises the score slightly.

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 scans a QBO Journal Entries CSV for anomalies, specifically round-number lines. It distinguishes itself from sibling tools like analyze_xero_journal_anomalies and analyze_qbo_journal_cleanup by specifying the exact input source and type of anomaly.

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?

Explicitly mentions when to use: when a user pastes QBO data and asks 'any anomalies?', 'look for round numbers', or 'anything suspicious'. It also clarifies this is a Tier-0 subset and that the paid product has additional capabilities, providing clear context and alternatives.

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