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

With no annotations, the description carries the full behavioral burden and does real work: it discloses the exact output composition (average, best, and worst price per event/market/player/line) and proactively calls out an edge case — soccer and 3-way markets return separate home/draw/away consensus rows. It omits data recency and pagination details, but the operation is clearly non-destructive and the get-style behavior is transparent.

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 sentence, followed by a tight return-value summary and a compact Args block. Every sentence earns its place; the only mildly expendable phrase, 'a sharp baseline for line-shopping,' doubles as usage context, so nothing is wasted.

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?

The description is sufficient for calling the tool: both parameters are documented, the output shape is stated, the 3-way market special case is covered, and the existing output schema supplies the rest of the return contract. The main gap is missing sibling differentiation — with 20 sibling tools including get_odds, best_line, and find_arbitrage, one sentence on when to choose consensus over those would fully close the loop.

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 description coverage is 0%, yet the Args section fully compensates: sport_key receives realistic examples ('baseball_mlb', 'soccer_epl') and markets receives both a format rule (comma-separated market_keys) and an example ('moneyline,totals'), plus explicit optionality. Both parameters gain meaning that the bare schema — type, title, default — does not provide.

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 precise verb+resource construction: 'Get consensus (average) odds across all bookmakers per market.' The notion of a consensus average across all bookmakers inherently distinguishes it from siblings like parlayapi_best_line (single best price) and parlayapi_get_odds (raw odds), and the stated return scope (average, best, worst per event/market/player/line) removes any ambiguity.

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?

Usage context is implied via 'a sharp baseline for line-shopping' — an agent can infer this tool is for market-wide price comparison. However, there is no explicit when-to-use/when-not-to-use statement and no named alternatives among the 20 siblings (best_line, find_arbitrage, get_odds), so routing to this tool over its neighbors relies on inference.

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