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

Beyond the read-only/open-world annotations, the description discloses the live external dependency (Kalshi only), the failure contract (returns available=false with a reason), and a directive to read available before trusting any field. It also explains the deliberate modeling constraint — no interpolation because the end buckets are open-ended — which is exactly the kind of behavioral context annotations cannot convey.

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 the edge-case/returns labeling is easy to scan, but the no-expected-value point is made twice — once as 'Deliberately does not compute an expected value' and again under 'Not covered: an expected value or a price inside a bucket' — with the open-ended-bucket rationale repeated in both. Trimming that duplication would tighten a description that is otherwise dense without fluff.

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 description compensates fully by enumerating the return fields (buckets[], medianBucketLabel, modeBucketLabel, vigPct, probabilityAtOrAbovePct, snappedThresholdUsd) and spelling out the conditional-return case. Combined with the unavailable-state contract, an agent has everything needed to call this correctly and interpret the result.

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%, so the baseline is 3, but the description adds real meaning: it restates the BTC default and explains that thresholdUsd snaps to the nearest real bucket boundary at or below the value, tying that to the returned snappedThresholdUsd. It also justifies why no in-bucket price is offered, which the schema does not.

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 ('Reads Kalshi's full live BTC or ETH year-end price ladder') and then enumerates exactly what it reports: median bucket, mode bucket, and probability at or above a boundary. That precision separates it from adjacent siblings like run_prediction_market_edge or run_odds_converter without the agent needing to open a 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 concrete trigger phrasings ('what does the market think BTC will be worth by year end?') plus a strong exclusion list — no expected value, no intra-bucket price, no other venues, no other horizons, no fees — which implicitly routes the agent elsewhere. It stops short of naming which sibling to use instead, so it falls just below the explicit-alternatives bar.

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