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

The description comprehensively explains the tool's deterministic multi-source approach, distinguishes LLM-derived emotion/intent as explicitly labeled, and mentions side effects (spends balance, requires auth). Annotations do not contradict; readOnlyHint=false aligns with the spending behavior.

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 detailed but slightly verbose, listing all 14 sources and the exact scores produced. It front-loads the core purpose well. Minor redundancy could be trimmed, but overall it's well-structured.

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 (14 sources, multiple outputs), the description covers all key aspects: what it returns (overall_sentiment, urgency, business_impact), how it handles emotion/intent, authentication, and costing. An output schema exists, so further details are handled there.

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 coverage is 100%, and the description adds contextual meaning: 'text' is described as 'customer feedback, review, or message', and 'budget_pence' as 'Optional max spend in pence'. This enriches the schema definitions.

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 performs sentiment analysis using 14 verified sources, distinguishing it from sibling tools which cover fraud, data extraction, code generation, etc. The verb 'analyze' and specific resource 'sentiment' are explicit.

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 specifies the input as 'customer feedback, review, or message' and notes it requires authentication and spends balance, providing clear context. It does not explicitly state when not to use or compare to alternatives, but given no other sentiment tools, this is sufficient.

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