pinnodds — Pinnacle odds

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

Annotations already establish readOnly, idempotent, non-open-world, so the safety profile is covered. The description adds genuinely useful context beyond that: the Trial-key quota of 100 requests/day and the diagnostic value after rate_limited/key_expired responses. It stops short of describing auth setup or whether quota resets on a rolling or fixed window, but the added behavioral context is substantial.

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?

Two sentences, front-loaded with the returned fields and then the actionable triggers. Every clause earns its place, including the parenthetical quota figure.

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 zero-parameter read tool with no output schema, the description fully compensates by enumerating the returned fields (plan, rate limits, expiry, today's request count) and by anchoring usage to two concrete scenarios. An agent has everything needed to call it correctly.

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?

The tool takes zero parameters, so there is no parameter surface to document; the baseline for a 0-param tool is 4. Nothing in the description misrepresents 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+resource (get account usage) and enumerates exactly what is returned: plan, rate limits, expiry, and today's request count. This is clearly distinguishable from the odds/events siblings, which all deal with sports data rather than account metadata.

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 explicit when-to-use triggers: call it before a long analysis to check remaining quota, or after a call returned rate_limited or key_expired. Names the concrete error conditions that select this tool, leaving nothing to inference.

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

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld), and the description adds real behavioural context on top: concise returns up to 5 alternate lines centred on the main line while detailed returns all, and 'one API request per call' flags the per-call cost. It does not disclose error/empty-book behaviour or payload shape (no output schema).

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 value, then periods, verbosity, id sourcing, and mode consistency in tightly packed clauses. No filler sentences; every line earns its place.

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 still conveys the shape of results (periods, line counts, concise vs detailed) and the cost of a call. Minor omissions remain, such as whether missing markets/periods are silently dropped, but nothing essential to correct invocation 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 description coverage is 0%, so the description carries the burden and does so: mode (live vs prematch, must match the discovery call), periods (0 = full match, 1 = first half/period, and so on), response_format (concise = 5 lines, detailed = all), and markets (team totals only on request). This adds meaning well beyond the bare enum and integer constraints.

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: 'Current Pinnacle prices for one event' with the exact market set (moneyline, spreads, totals, team totals). It is clearly distinct from siblings like get_events (id lookup) and get_prematch_lines (prematch-only board).

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 concrete routing: event ids come from get_events or get_odds_drops, and 'pass the same mode you used to find the event' since live and prematch are separate boards. It does not explicitly say when to prefer this over get_prematch_lines, so it falls short of a full when/when-not/alternatives statement.

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

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

Adds real context beyond the readOnly/openWorld/idempotent annotations: results are capped and the trailer reports how many were hidden, and each call costs one live API request against the plan with an instruction to reuse ids. That cost and truncation disclosure is exactly the kind of behavior an agent cannot infer from the schema or annotations.

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-loads what the tool returns, then the routing instruction, then filtering syntax, then cost/pagination caveats. Five dense sentences with no filler; each one carries distinct information.

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 still characterizes the return (compact rows, moneyline, response_format effect) and the truncation trailer, and warns about per-call cost. For a 5-param, read-only search tool an agent has everything needed to call it correctly.

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 already 80%, so the baseline is 3. The description goes further on the highest-value parameter by explaining query semantics (space-separated, all words must match league/home/away, case-insensitive) with a concrete example, though limit's cap is only referenced indirectly as 'capped'.

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 (list events) with scope qualifiers (live or upcoming/prematch, one sport) and output shape (compact rows with full-match moneyline). It is clearly distinguishable from get_event_odds (odds detail) and get_prematch_lines.

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?

Explicitly routes the agent: 'Use it to find event ids before calling get_event_odds' gives a concrete when-to-use and names the follow-on tool. It does not, however, address when to prefer it over the overlapping get_prematch_lines for upcoming fixtures, so the guidance is clear but not exhaustive.

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

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

Beyond the readOnly/openWorld/idempotent annotations, the description discloses important behavioral context: that an empty board can be a deliberate withholding when upstream goes quiet past a threshold, and that REST responses carry X-Data-Status and X-Data-Age-Ms to distinguish fresh/stale/unknown. This adds substantial interpretative value for the agent.

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 description is front-loaded with the core question and then answers when to call and how to interpret results. It is well structured and nearly every sentence adds value, though the final sentence ('This tool is how you find out which of the two it was') is somewhat redundant given the preceding explanation.

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 and no parameters, the description carries the burden of explaining what the tool returns. It describes the reported signals and header semantics well, but does not specify exact return field names or types. For this diagnostic use case that is largely sufficient, though slightly incomplete.

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?

The tool takes zero parameters, so there is nothing for the description to add about inputs. The baseline for zero-parameter tools is 4, and the description correctly does not waste space restating an empty schema.

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 states a specific diagnostic verb and resource: checking whether the odds feed is healthy, and enumerates the exact signals reported (upstream status, live event count, last write freshness, prematch board serving). It is immediately distinguishable from siblings like get_event_odds or get_prematch_lines, which retrieve odds rather than report feed health.

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 an explicit trigger: 'Call this when odds look stale or a board came back empty.' It also clarifies a common false alarm (empty board not necessarily an outage). However, it does not name alternative tools or state when not to use it, so it falls short of a full 5.

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

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so safety is covered. The description adds real value beyond them: result ordering ('newest drops first'), returned fields (from/to price, drop percentage), and cost ('One API request per call').

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?

Five short sentences, front-loaded with the core concept and return shape, then defaults, then tuning, then filters. No filler and every clause carries information.

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 and 8 parameters at 13% description coverage, the description does most of the necessary work: what the signal is, ordering, returned fields, defaults and filter dimensions. It omits the meaning of `mode` and `response_format`, which are the remaining gaps for a caller.

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 only 13%, so the description must compensate, and it largely does: it explains the semantics and defaults of `max_age_sec` and `min_drop_pct`, enumerates the market values, and describes the period and sport filters. It leaves `limit`, `mode` (live vs prematch) and `response_format` unaddressed, so it is not fully compensating.

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?

Names a specific signal ('prices that dropped sharply against their own recent history — the 'steam' signal') rather than restating the tool name. An agent can distinguish it from get_event_odds and get_prematch_lines without opening any 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?

Gives concrete tuning guidance — defaults of last 10 minutes at 5%+, and explicitly how to broaden results via `max_age_sec` or `min_drop_pct`. It stops short of naming a sibling tool or stating when a different tool is the better choice.

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

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds a genuine behavioral constraint not in the annotations — that results are scoped to prematch events only and span all periods of a market. It omits response size/pagination behavior for what is potentially a large 'all lines' payload, keeping it short of a 5.

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?

Three tight sentences in a deliberate order: what it returns, when to prefer it over the sibling, then the prematch-only exclusion. No wasted words and the core purpose is front-loaded.

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 two-parameter read tool the routing and scope information is strong, and no output schema exists so return semantics must come from the description — which it partially supplies ('all spreads, or all totals, etc.'). The remaining gap is that parameter identity and allowed market_type values are left entirely to the schema.

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% for both parameters, so the description must compensate, and it does not: neither event_id nor market_type is named, and the enum values (money_line, spreads, totals, team_total) and the 'totals' default are never referenced. The phrases 'spreads'/'totals'/'handicap' loosely evoke the market concept but do not tie meaning to a specific parameter.

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 concrete action and resource: 'Every alternate line for ONE market of ONE prematch event ... across its periods.' It explicitly distinguishes itself from the sibling get_event_odds ('centred selection is not enough'), so an agent can route correctly without opening either 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?

Gives explicit when-to-use ('when get_event_odds' centred selection is not enough — e.g. to find the price at a specific handicap') and a when-not ('prematch only; for live events use get_event_odds with response_format=detailed'). Both the alternative and the selecting condition are named.

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

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

Annotations already declare readOnlyHint, idempotentHint and closed-world, so the safety profile is covered. The description adds a genuinely useful trait outside the annotations — 'Costs no API quota' — plus the domain note that Soccer (1) has the largest board. It does not describe return shape, but the id/name pairing is implied in sentence one.

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?

Three short sentences, front-loaded with the identity statement, then the trigger, then the operational caveat. Every sentence carries distinct information; nothing is repeated from the schema or annotations.

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 zero-parameter lookup with no output schema, the description supplies what is missing: what the return contains (sports and their numeric ids), when to reach for it, its quota cost, and a coverage caveat. An agent has everything needed to call it correctly.

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?

The tool takes zero parameters, which is the baseline-4 case. There is no argument syntax to explain, and the description correctly spends its words on when to call rather than inventing parameter guidance.

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 ('List the sports pinnodds covers') plus the payload detail that matters ('with their numeric ids'). It also distinguishes itself from get_events by directing board-narrowing to that sibling's `query` parameter, so an agent can tell the two apart without opening either 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?

Gives an explicit trigger ('Call this first when the user names a sport and you need its id, or to confirm coverage') and names the alternative path for the adjacent task (use `query` in get_events to narrow). Both when-to-use and when-to-go-elsewhere are covered.

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

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

Annotations already declare readOnly, idempotent and closed-world, so the safety profile is covered. The description adds genuinely new operational context: the call 'Costs no API quota', which materially affects how freely an agent may invoke it. It does not, however, describe the shape of returned results or any rate/latency behavior.

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?

Two tight sentences: the first defines scope, the second defines the use case and a cost constraint. Every clause carries information and the scope statement is front-loaded.

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?

No output schema exists, so the description ideally would hint at the return shape (e.g., doc snippets or references). Scope, intended use, and quota cost are all present, making it largely adequate for a simple two-parameter search tool.

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% for both parameters, so the description carries the burden. It partially compensates by enumerating the topic space a query can target, but says nothing about the `query` string's role/length or the `limit` parameter and its default of 3 / maximum of 5.

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 (Search) plus the exact resource domain (pinnodds API reference) and enumerates the covered content: endpoints, parameters, rate limits, plans, WebSocket/SSE feeds, sport ids, market shapes. This cleanly separates it from the data-fetching siblings like get_event_odds or get_events.

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 an explicit selection rule: use it for 'how do I…' questions about the API itself 'rather than about odds'. That excludes the odds/data siblings by category, though it does not name any specific sibling tool or state any prerequisite for use.

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