Venue profile: everything ByKaranteli records about one exchange

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds one genuinely useful behavioral fact — calling without 'venue' returns the list of recorded venues — and enumerates the payload because no output schema exists. But it says nothing about data freshness, historical depth, or whether values are point-in-time snapshots versus aggregates, which matters for a profile spanning uptime and event logs.

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 call trigger is front-loaded in the first clause, and every subsequent clause adds a distinct data category rather than filler. It is a single long sentence, though, and the parenthetical venue list plus trailing '...' hedge make it denser than necessary — a short bulleted list of returned sections would read faster.

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?

With no output schema, the enumeration of returned sections is exactly what the agent needs to judge whether this tool answers the question, and the default no-arg behavior is disclosed. What remains uncovered is freshness/coverage ('ByKaranteli records' hints at a proprietary dataset but its completeness and update cadence are unstated) and the size of the payload, which could be large for a full venue profile.

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% for the single optional 'venue' parameter, so the baseline is 3. The description does add value by listing recognizable venue names (Bybit, OKX, Gate, KuCoin, HTX, Bitget, MEXC, BitMEX, Hyperliquid) that help the agent map a user's mention to an id, but it does not state the accepted id casing/format or whether fuzzy names are matched.

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+resource ('venue profile' / everything recorded about one exchange) and enumerates the contents: contract counts, open interest, funding, leverage ladders, deposit/withdrawal networks, fee schedule, uptime and event log. That is far more concrete than the title alone. It does not, however, distinguish itself from overlapping siblings such as get_venue_markets, get_venue_share, get_withdrawal_status or get_fee_table, whose data appears to be folded into this profile.

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 trigger is explicit: 'Call this when the user asks about a specific exchange', followed by the concrete categories of questions it answers. It also clarifies the no-argument behavior (returns the list of recorded venues). What is missing is when-not guidance — nothing tells the agent to prefer get_venue_markets or get_withdrawal_status for narrower questions, even though those siblings exist.

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