One whole market

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

Annotations already declare readOnly, openWorld and idempotent, so the bar is lower, yet the description adds real context: a TILLA_API_KEY is required, answers are capped at 200 columns, and `series_next_offset` signals the next page. It does not explain what the different layers actually return or how offset paging is driven, but the added operational context is well above baseline.

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?

Dense, front-loaded and nearly waste-free: the core promise comes first, then parameter semantics, then the pagination and auth constraints. Some fragmentary phrasing ('on one clock', 'At most 200 columns an answer') costs a little clarity.

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 6-parameter, open-world data read with no output schema, the description covers the essentials an agent needs to call it: required key, market id source, layer/period/related semantics, and pagination behavior. The uncovered items (valid lane values, the meaning of limit versus the 200-column cap, shape of returned series) are the remaining reasons it is not a 5.

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 0%, so the description must carry the load, and it does for most parameters: market (id source plus btc/nvda/eurusd/gold examples), layer (raw|derived|node|deep|all), period (full enum), and related (with the btc ETF/miner example). Gaps remain for `lane` (no valid values or meaning of the 1min default) and `limit` (its relation to the 200-column cap is never stated).

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 concrete verb+resource: retrieves every series of one market across a lane in a single call, and implicitly distinguishes itself from tilla_markets by noting `market` is an id taken from that tool. The phrase 'on one clock' and the layer jargon slightly blur the exact payload, but an agent can tell what comes back at a high level.

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?

It gives a useful routing hint ('market is an id from tilla_markets') and explains when to set related=True, but says nothing about when to prefer this over close siblings like tilla_window, tilla_latest, or tilla_tick, which all sound like time-sliced data reads. Usage is implied rather than disambiguated.

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