Prediction-market strike ladders on an instrument

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

Goes well beyond the annotations: prices are venue prices in 0-100 points and never CoinRithm forecasts, tradedRecently:false is not a live price, groups:[] means no contracts, coverage.degraded:true means the read failed, venue outcome ids are omitted, and no API key is required. These are exactly the failure-mode and data-provenance details an agent cannot get from readOnlyHint/destructiveHint.

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 purpose is front-loaded in the first clause and every sentence carries information, but the description is a dense semicolon chain that mixes purpose, parameter guidance, and output-shape notes. Slightly reorganizing output caveats (groups:[], coverage.degraded) would improve scanability without losing content.

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 read-only, 6-parameter tool with an output schema, an agent gets scope, provenance, degradation signals, and an alternative path for ids. It could be stronger with an explicit statement of which sibling to use when a live price is actually needed.

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 already 100%, so the baseline is 3. The description still adds actionable meaning for `detail` (outcome ids are omitted unless detail=full) and clarifies that `id` is a slug/ticker rather than a numeric coinId, plus that referenceRelation/observation semantics are documented once in referenceNotes.

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 resource (prediction-market strike ladders), its scope (contracts on a crypto/TradFi/index price), and its organization (grouped by expiry and settlement source, one ladder per venue series, soonest expiry first). The example 'will BTC be above $X at time T' pins down the concept and separates it from quote-style siblings like pm_quote.

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 clear routing advice in-context: 'use detail=full or pm_data_event on the ladder's event' for venue outcome ids, and 'reference names the series to read' for reading prices. It also implicitly excludes itself from price lookup ('No live price is included'), but never states explicitly when to prefer a sibling such as pm_quote or discover_pm_markets.

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