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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is free. The description still adds real behavioral context: symbol and non-preset q/f values are normalized, a freshness field is returned, suggestedNextCalls come pre-filled, and analogues are framed as "dated look-alikes, not a tested rule" that do not invent levels from P90/P10. It omits error modes and any latency/cost behavior, keeping it short of a 5.

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?

It is front-loaded with the purpose and the replacement list, which is good, but it is a single dense run-on paragraph mixing return-field inventory, sibling routing and a promotional URL with UTM tracking parameters. The marketing link at the end does not help an agent invoke the tool and dilutes an otherwise information-dense block.

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?

There is no output schema, and the tool returns a large composite payload; the description compensates by enumerating the major returned sections (brief contents, closest twins, neighbour vs all-history band, analogue map, range ledger, freshness, suggestedNextCalls). For a six-parameter aggregate tool that is close to complete, with only minor ambiguity about the exact shape of each section.

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% with enums and defaults documented for all six parameters, so the schema carries the load and baseline 3 applies. The description adds only the normalization note for non-preset q/f, which arguably sits in mild tension with the enum that lists only presets, and says nothing extra about anchorTs or limit.

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 specific verb-and-resource framing ("One call for the whole candle-memory picture of a BTC, ETH or SOL window") and then explicitly names the three siblings it supersedes: get_candle_market_snapshot, what_is_odd_in_candle_memory, and get_candle_analogue_map. An agent can place this tool in the sibling set without opening any schema.

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 an explicit call trigger ("Quote brief before answering about that market") and a hard exclusion for a sibling: "Call check_candle_order only when the trader already named those three prices." It also routes the backtesting use case away to an external MCP, so the when-not conditions are covered as well as the when.

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