Prediction Market Intelligence

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description's job is to add behavior — and it does: it explains that supplying amount walks the book level by level for a market order and returns shares filled, average/worst price, slippage, taker fee and breakeven probability. It still omits data freshness/latency and error 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 sentences, front-loaded with the routing trigger and then the return contract. Every clause carries information — no filler, no restatement of the title 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?

With no output schema, the description must carry the return contract, and it does: it enumerates the book fields and the full fill-cost payload. Combined with annotations handling safety, an agent has everything needed to call and interpret it.

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; the description adds genuinely new meaning by tying amount to order semantics ('dollars to spend when buying, shares when selling') and framing it as a level-by-level walk rather than a snapshot, plus noting the default outcome. That clarifies interaction between side and amount beyond the schema text.

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 (retrieve the live order book and compute fill cost for one outcome) and is clearly separable from sibling market-data tools like pm_market. An agent can tell what it produces — best levels, spread, depth, fill simulation — without opening the 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?

Opens with explicit user-intent triggers: liquidity, real cost of a given-size trade, price impact, or viewing the book. This is strong when-to-use guidance, but it names no alternative (e.g., pm_market for plain price/quotes) and gives no when-not conditions.

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, destructiveHint=false and openWorldHint, so the safety profile is covered. With no output schema, the description usefully fills that gap by describing the returned content in both modes, and adds a real data caveat ('Traders appear by public username when they set one'), though it omits result limits/pagination and any cost or rate considerations.

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 usage trigger, then the return contract, then the wallet handoff to pm_portfolio — a sensible order with no filler sentences. The trigger enumeration is long and slightly redundant ('who is buying or selling' / 'where the money is going'), which keeps it from a 5.

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 4 optional parameters, full schema coverage, no output schema and rich annotations, the description is nearly complete: it explains both invocation modes, the fields returned in each, and where to go next. Only secondary details (result caps, sorting of the largest trades, time-window interaction with min_usd) are left unstated.

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 a genuinely non-obvious conditional that the schema does not encode: min_usd applies only 'without a market', and the no-market mode is what produces cross-Polymarket whale trades. It also confirms market accepts a link or slug, matching the 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 concretely enumerates what the tool produces (dollars traded and net direction per outcome, distinct wallets, largest trades, top movers, biggest holders) and states the two modes (with vs. without a market), which is far more than a restated title. It names one sibling (pm_portfolio) as a follow-up, but never distinguishes itself from pm_moves or pm_leaderboard, whose scopes ('why its price moved', leaderboard-style rankings) appear to overlap.

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 opens with an explicit trigger list ('Use this when the user asks who is buying or selling... why its price moved... what the whales are doing'), which is genuine when-to-use guidance, and it routes wallet-level depth to pm_portfolio. However, it gives no when-NOT-to-use exclusions and does not tell the agent how to choose between this and pm_moves/pm_leaderboard when the question is ambiguous.

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/openWorld/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: the ranking basis (profit or volume) and that results include usernames plus wallet addresses intended for chaining into pm_portfolio. It stops short of noting data freshness or pagination limits beyond the schema's 25-row cap.

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 trigger condition and two sentences total, both earning their place. The long inline enumeration of categories is slightly padded and duplicates the schema enum, but it stays readable.

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 compensates by stating what comes back (ranked leaderboard, usernames, wallet addresses) and how to use it. For a read-only ranking tool with all four params documented, nothing material 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 100% and three of four params are enums with documented defaults, so the schema already carries the semantics. The description enumerates the period and category values but adds no format or interaction detail beyond the schema; baseline 3 applies.

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 verb and resource ('Returns Polymarket's own leaderboard ranked by profit or by volume') and pins the domain to Polymarket traders, which separates it cleanly from pm_market, pm_search, and the other 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?

It gives explicit trigger phrasing ('who the best or biggest... traders are, who made the most money today, this week, this month or all time, or who leads in a category') and names the downstream alternative by stating wallet addresses are 'to pass to pm_portfolio'.

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 read-only/idempotent/openWorld, and the description adds real value beyond them: the four-state resolution lifecycle (not proposed / proposed in challenge window / disputed / resolved), verbatim resolution rules with a named source, and the multi-outcome sum-to-100¢ check. It does not mention auth scoping or rate limits, so it is not a full behavioral profile.

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 trigger, then the return payload, then the optional-parameter guidance. The return enumeration is dense but every item (fees, rules verbatim, resolution status) is a distinct capability rather than padding; it is slightly long but not wasteful.

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 carries the full burden of describing returns, and it does so thoroughly: prices with bid/ask/spread, 1h/24h/7d/30d change plus 30-day range, volume/liquidity, taker fees, rules, and live resolution status. An agent has everything needed to call it 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 meaning the schema doesn't carry: 'add outcome to drill into one' explains the conditional purpose of the optional parameter, and the multi-outcome behavior (lists every outcome, checks that prices sum to 100¢) tells the agent why it might set it.

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 names a specific verb+resource ('one Polymarket market or event') and enumerates exactly what it reports: price, resolution rules, proposal/dispute status, end time, fees, and price movement. The scoping word 'one' implicitly distinguishes it from sibling aggregations like pm_moves and pm_leaderboard, so an agent can route without opening the 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 states a clear triggering condition ('Use this when the user asks about one Polymarket market or event') and routes the agent to pm_search as the source of slugs, plus tells it to add 'outcome' to drill into a single leg of a multi-outcome event. It stops short of an explicit when-not-to-use clause (e.g. 'do not use for a portfolio of markets'), so it is strong but not fully 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?

Annotations already declare this a read-only, idempotent, open-world read, so the safety profile is covered. Beyond that, the description discloses non-obvious behavior: the candidate universe is capped at the 300 most-traded open markets, settling/live-game markets are filtered out, and the returned fields are enumerated (old/current price, pp move, 24h volume, slug). It stops short of covering pagination or rate limits, but the exclusions and universe cap are genuinely useful context.

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?

A single dense paragraph, but front-loaded with the triggering user questions before the mechanics, and every sentence carries information (universe, fields, exclusions, sibling handoff). The middle clause listing return fields is slightly overloaded but still earns its place given there is no output schema.

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 compensates by enumerating the returned fields and their interpretation, plus the market universe, the exclusion rules and the default volume floor implied by 'most-traded'. 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 schema already documents all five parameters including defaults and ranges, making 3 the baseline. The description echoes window/direction/include_games semantics and implies the min-volume behavior via '300 most-traded', but adds no syntax or edge-case detail beyond the schema text for limit, window, direction or min_volume_24h_usd.

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 ('Ranks the 300 most-traded open markets by price change') with the exact scope of the ranking, and differentiates itself from pm_flow, which is positioned as the follow-up tool for attribution. An agent can select this over pm_book, pm_market or pm_flow 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?

Opens with an explicit trigger list ('what is moving, trending or changing... what moved overnight or this week... biggest gainers and losers') and names the alternative for drill-down ('pm_flow shows who moved it'). It also states the negative case: settling markets and live sports games are excluded unless include_games is true.

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, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: 'Public on-chain data only', which signals no authentication or private data is involved, and it enumerates what data is returned.

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?

Usage guidance is front-loaded and every sentence carries information — intent triggers, accepted inputs, returned fields, and data source. It is a dense single paragraph rather than over-long, though splitting the return contents into a list would improve scannability.

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, so the description carries the return-value burden and does so thoroughly: track record metrics, open positions with entry/current price and unrealized P&L, event-grouped exposure, unredeemed settled winnings, and recent trades. An agent knows both what to pass and what it will get back.

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 100% and the single parameter already documents all three accepted forms (0x address, profile link, username). The description restates those accepted input forms, reinforcing but not extending the schema, so the baseline of 3 applies.

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 (retrieve a wallet's holdings and track record) and frames it around concrete user intents — 'what a Polymarket trader or wallet holds, how good a trader is'. It also anchors itself against the sibling pm_flow by mentioning wallets seen there, so it is distinguishable from pm_book, pm_leaderboard, etc.

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 trigger conditions (user asks about holdings, trader quality, or sizing up a wallet from pm_flow). It does not state when not to use it or name a concrete alternative tool for overlapping needs, so it stops short of a 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, destructiveHint=false and openWorldHint, so the safety profile is covered. The description still adds real value beyond them by disclosing the result shape (all outcomes, current prices, 24h volume, end dates) and the meaning of status='resolved' ('how they settled'), which matters because there is 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?

Three sentences, front-loaded with the primary directive 'Use this first when...', and every clause carries information (search modes, return fields, status usage). The middle sentence is dense and runs long, but nothing is filler; a small trim would earn a 5.

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 3-parameter read-only search with no output schema, the description covers the gaps that matter: when to reach for it, both query modes, what the response contains, and how to get resolved/settled markets. An agent has everything needed to invoke 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 100%, so the baseline is 3. The description adds meaning beyond the schema by explaining the semantic intent of the query (topics, likelihood questions, bare market names) and by interpreting status='resolved' as past markets plus their settlement outcome, which the enum alone does not convey.

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 ('Searches every Polymarket market by keyword ... or by a polymarket.com link') and enumerates what comes back (events, outcomes, prices, 24h volume, end dates, slug). It also positions itself relative to the siblings by framing itself as the first call whose slug feeds 'the other tools', so an agent can distinguish it from pm_market/pm_book without opening 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?

Gives explicit trigger conditions: 'Use this first when the user asks what Polymarket thinks about a topic, how likely something is, or names a market without a link.' That is strong when-to-use guidance, but it never states when NOT to use it or names a concrete alternative tool for a specific case, so it falls short of the 5 bar.

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