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

Annotations only declare a safe read; the description goes far beyond them by disclosing the 7-exchange fetch set, the exact status thresholds (0.25%/1%), the insufficient condition (fewer than 3 comparable peers, inverse/dated/unlisted contracts excluded), and the explicit promise never to guess. This is exactly the behavioral context annotations cannot carry.

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-loaded with the core operation, then usage, returns and edge cases in a logical order. It runs long and repeats the 'insufficient / never a guess' failure behavior twice (in the status list and again under edge cases), which is minor redundancy rather than filler.

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 description properly enumerates all return fields (status, summary, median, peerMedian, spreadPct, deviationPct, sources, quotes, thresholds_pct, as_of) and covers failure modes for a tool that depends on live multi-venue data. Nothing an agent needs to call it correctly or interpret the result is missing.

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 already documents both parameters with examples, so the baseline is 3. The description adds real meaning on top: the symbol must be that venue's own perp symbol and is constrained to 1–60 characters, exchange must be a known code, and only comparable USDT/USDC-margined perps are valid inputs.

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 — a cross-exchange agreement check for one perpetual futures price — and enumerates the exact reference set of 7 venues plus the outputs (median of peers, spread, deviation from median). An agent can immediately tell this apart from price-fetching or arbitrage siblings.

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 a concrete trigger scenario ('Use before acting on a live price: "is this Bybit BTC price in line with the market?"') and explicit scope exclusions (order book depth, funding/basis, spot prices, no claim about which exchange is right). It never names a sibling tool as an alternative, so routing against run_cross_venue_arbitrage or run_spread_reader is left to inference.

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