get_candles

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

Annotations already declare read-only, idempotent, non-destructive, open-world. The description adds meaningful caveats beyond that: adjusted prices are 'not verified total returns', the 'before' boundary is 'unverified', and 'complete' covers only the page chain, not historical coverage. That is exactly the kind of epistemic context an agent needs; a pagination/size caveat beyond max 200 would round it out.

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?

Front-loads purpose, then uses clear Args/Returns structure with no filler. The Returns section is somewhat dense and restates scope ('Raw provider payload for existing calls'), but each sentence adds a real constraint or caveat rather than padding.

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 7-parameter, paginated, provider-backed data tool with an output schema, this covers params, paging semantics, return shape, and reliability caveats — enough to call it correctly. The remaining gap is the absence of sibling routing guidance for choosing this versus quote/indicator tools.

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 0%, so the description carries the full burden, and it does: it explains symbol format examples, interval enum values, count max/default, the meaning of 'adjusted', the nature of 'before' as a provider cursor, and that start/end are inclusive candle-local YYYY-MM-DD labels. Every one of the 7 parameters gains meaning not present in the schema.

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?

States a specific verb and resource — 'Get candlestick chart data (OHLCV) for a stock (Toss)' — which is unambiguous and clearly different from snapshot/quote tools by naming OHLCV and the provider. It does not explicitly contrast with siblings such as get_quote or get_technical_indicators, so it falls short of a 5.

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?

Gives procedural guidance for paging ('One page per call', 'Merge pages ascending by timestamp and deduplicate'), which implies when the tool is appropriate. However, it never says when to prefer this over get_quote, get_technical_indicators, or compare_price_performance, and offers no guidance on choosing interval or date ranges.

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