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

Well beyond the readOnlyHint annotation, the description discloses that technicals are 'computed in-house from candles' (provenance), that on-chain data is conditional ('when the symbol is a tracked chain'), that the narrative is 'grounded ... with citations' (generative behavior), and that a per-section status list 'distinguishes an empty section from a failed feed' (failure semantics). The 'same ... as' cross-references are consistency guarantees. No contradiction 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?

The core purpose is front-loaded and every clause carries distinct information — each enumerated data type maps to a sibling tool or a behavioral caveat. However, it is one extremely long run-on sentence with heavy em-dash packing; a bulleted or sectioned structure would improve scannability without losing information.

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 tool aggregating roughly fifteen data types with an output schema present, the description covers the full content breadth, conditional availability, computation provenance, consistency with sibling tools, and per-section failure signaling. Nothing an agent needs to predict the tool's behavior or interpret its output sections is omitted.

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 schema already documents symbol with examples ('ETH', 'BTC'). The description reinforces the single-symbol scope ('for one symbol') but adds essentially no new parameter semantics beyond what the schema provides, so the baseline of 3 applies.

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 opens with a precise verb+resource ('Aggregated single-coin dossier') and exhaustively enumerates the content sections. It actively distinguishes itself from siblings by cross-referencing 'the same enriched line as market_quotes' and 'the same numbers as ta_technicals', so an agent can tell this aggregation tool apart from the single-purpose tools without opening their schemas.

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 aggregation framing plus 'for one symbol (e.g. 'ETH')' makes the intended use clear: a comprehensive single-symbol overview. It names the overlapping siblings (market_quotes, ta_technicals) and signals that their data is duplicated here. However, it never states an explicit when-not condition, e.g. that an agent needing only the current price should call market_quotes directly instead of this heavier tool.

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