kite-mcp

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

Annotations confirm read-only safety; description adds valuable content context by previewing return fields (quantity, average price, last price, P&L). This helps the agent anticipate data structure even though output schema exists. No contradictions 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?

Single efficient sentence front-loaded with action verb. Every clause earns its place: scope ('all holdings'), location ('in the portfolio'), and specific return fields. Zero waste despite information density.

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?

Complete for a simple read operation: 0 parameters, annotations cover safety profile, output schema exists for structure, and description adequately previews the data payload without redundancy.

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?

Zero parameters per empty schema; baseline 4 applies as there are no parameters requiring semantic description. Description correctly implies no filtering arguments needed.

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?

Excellent clarity with specific verb 'Get', resource 'holdings', and scope 'all holdings in the portfolio'. Implicitly distinguishes from sibling get_positions (active trades vs long-term holdings) and get_orders (transactions vs current portfolio).

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?

Implies usage for portfolio overview by mentioning specific return fields (P&L, average price), but lacks explicit when-to-use guidance distinguishing from get_positions or whether this requires prior authentication/kite_login.

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