kite-mcp

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

Annotations confirm readOnlyHint=true and non-destructive nature. The description adds crucial behavioral context not in annotations: the fallback logic to holdings/positions when market data API fails. This data source switching is significant runtime behavior. It does not mention rate limits or caching, but given annotations cover the safety profile and output schema exists (per context signals), this provides good supplementary behavioral detail.

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?

Two sentences with zero redundancy. The first sentence front-loads the core function (retrieve OHLC/price), while the second adds the critical fallback caveat. Each sentence earns its place - the first defines capability, the second warns about data source variance. No fluff or tautology.

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 has only one parameter and output schema exists (per context signals), the description successfully captures the essential business logic (OHLC retrieval) and the key behavioral quirk (fallback to positions). For a read-only data retrieval tool of this scope, the combination of annotations, description, and output schema provides sufficient completeness, though parameter documentation is weak.

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?

With 0% schema description coverage, the description fails to adequately compensate. While it mentions 'for instruments' implying the target, it provides no details on the expected format (Identifiers? Tickers? ISINs?), the array structure, or quantity limits. The parameter 'instruments' is completely undocumented in the schema, requiring the description to carry this burden, yet it only nominally references the concept.

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 retrieves 'OHLC (open, high, low, close) and last price for instruments' - specific verb and resource. It distinguishes from sibling tools like get_holdings/get_positions by explicitly stating it 'Falls back to holdings/positions data if the market data API is not available,' clarifying the relationship between market data and position data retrieval.

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 provides implicit guidance through the fallback mechanism explanation, indicating this tool can serve as a resilient source when market data is unavailable. However, it lacks explicit guidance on when to choose this over get_quote (which also retrieves price data) or get_historical_data (which likely provides past OHLC), leaving the agent to infer based on subtle naming differences.

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