Election Odds Desk

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

Annotations already mark it read-only and non-destructive, and the description adds the substantive behavioral facts: fees are included, results are "ranked by price only", and a cheapest venue is named. No mention of coverage gaps or what happens when a contract is missing on one venue, which is the main remaining blind spot.

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 three quoted intents before the definition, then scope and ranking rule. Some duplication between the example list and the supported-domain sentence (sports and races appear twice), but nothing is padded.

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 does the necessary work by stating what comes back (per-venue cost for one contract, fees included, cheapest named, price-ranked). A caller can act on it; only edge-case behavior and result-shape detail are absent.

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 all five params are already documented with examples. The description adds only category-level mapping (sports -> team/league/matchup, races -> state/slug/district, "next Fed meeting"), not the free-form-vs-structured relationship or whether params combine — 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?

States a specific verb and resource: "the cost to buy one contract including each venue's taker fee, with the cheapest named" across Kalshi, Polymarket US and Novig. That fee-inclusive comparison framing clearly separates it from the sibling odds tools (race_odds, market_pulse, fed_rate_odds).

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?

Quoted example queries ("where is it cheapest to buy", "cheapest venue for the Georgia Senate race") and an explicit supported-domain list (sports games, 2026 midterms, next FOMC meeting) give a clear entry condition. It never says when to prefer a sibling such as race_odds for raw odds instead, so no exclusion guidance.

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 establish readOnlyHint=true and destructiveHint=false, and the description adds meaningful context beyond that: the data is live Kalshi pricing, scoped to remaining 2026 FOMC meetings, and includes a gap-in-pp comparison against Polymarket and CME futures. It stops short of stating refresh cadence, latency, or coverage caveats for meetings beyond the next 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?

Two sentences, front-loaded with the usage trigger before the payload inventory. The second sentence is a dense list of five returned elements, which is slightly crowded but each clause maps to a distinct output component rather than filler.

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 zero parameters, an output schema present, and annotations carrying the safety profile, the description supplies everything else an agent needs: when to call it, what venue the odds come from, the time horizon, and what the cross-venue gap represents. Nothing material is missing for a correct invocation.

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 disambiguate and the baseline is 4. The schema is empty and no parameter-level meaning is required.

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 resource (Fed/FOMC rate odds) and enumerates its concrete payload: the next meeting's strike breakdown, days-until, rate path, current fed funds rate, and a cross-venue check. It quotes the exact user questions it answers, which cleanly separates it from siblings like base_rate_gap and market_pulse.

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 'Use for' trigger covering both 'will the Fed cut, hold or hike' and 'next FOMC meeting odds', giving the agent a clear selection condition. It does not name an alternative tool or state when not to use it, so the routing guidance 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 readOnly/openWorld/non-destructive, so the description is free to add the non-obvious part — tier-based response gating: composite+regime+2 categories unauthenticated, 4 signed-in, all six with Pro. That is exactly the kind of auth/entitlement behavior an agent cannot get from the schema, and it materially affects how results should be interpreted or explained to a user.

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 dense sentences: the return payload and its components come first, then entitlement gating, then trigger phrases. Every clause carries information; nothing is boilerplate.

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 bears full responsibility for describing return values — and it does, enumerating the composite, regime, and category scores plus which tiers receive how many. Combined with the entitlement disclosure, an agent has everything needed to call 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% and the single `topic` parameter is fully described there, including the enum. The description only reinforces that macro is "the only topic", adding no syntax, format, or default behavior beyond the schema — baseline 3 for a high-coverage 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?

States precisely what is returned: a 0–100 US macro-health composite, a regime call, and six named category scores (growth, labor, inflation, rates, liquidity, sentiment). The resource is unambiguous, but the description never contrasts itself with siblings (best_price, fed_rate_odds, race_odds, senate_map), relying on domain obviousness for differentiation.

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?

Provides three concrete trigger phrasings ("how is the US economy", "macro regime", "risk-on or risk-off") that map directly onto the tool, which is clear usage context. It stops short of explicit exclusions or naming alternative tools, so it lands at 4 rather than 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 cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true). Beyond that, the description discloses the payload contents (every leg's price, volume, link, seat holder, rating, forecaster bands) and asserts a data-quality guarantee ("Prices are never estimated"), which is real added context. It omits freshness/caching or coverage caveats for races with no market, keeping it at 4.

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 use case, then the resource, then swap-format flexibility, then the return contents — every clause carries information. It is a long, dense sentence and the parenthetical adds clutter, but nothing is redundant filler.

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 only one parameter and no output schema, the description carries the return-value burden and does list the returned fields plus a reliability guarantee, which is enough to call the tool confidently. Missing only edge-case behavior for ambiguous or nonexistent races.

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% and the schema description already enumerates state name/code, slug, and district with the "TX-34" example. The description restates the same set ("by state, code, slug or district") without adding new syntax, disambiguation rules, or normalization behavior, so the 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?

States a specific verb+resource with scope: "Live Kalshi odds for one 2026 Senate, governor or competitive House race." The word "one" plus the race-type enumeration implicitly separates it from senate_map (all races) and fed_rate_odds (rate markets), 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?

Leads with "Use for ..." and supplies two concrete trigger queries ("who wins the Kansas Senate race", "Michigan governor odds"), which is clear positive guidance. It does not name alternatives or say when NOT to use it (e.g., other years, national maps), 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 and openWorldHint, so safety is covered; the description adds genuinely new behavior: results are sorted closest race first, unpriced seats return null rather than an estimate, and each seat carries a page URL. The only missing piece is whether coverage is guaranteed for all seats or rate-limited.

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, front-loaded with the use case before the payload contents and the null-price guarantee. Slightly dense with field enumerations, but no sentence is filler.

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 return-value burden and does so: field list, ordering, URL per seat, and null semantics for unpriced seats. An agent knows what it will get back without invoking the 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the schema cannot be improved upon. The description correctly implies a parameterless full-map call.

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 resource (every 2026 Senate seat) and enumerates exactly what each row contains — holder/role, structure rating, forecaster bands, Kalshi price, page URL. It is unmistakably about Senate elections, but it never differentiates itself from the sibling race_odds, which an agent could plausibly pick instead.

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 phrasing ("2026 Senate map", "which Senate seats are toss-ups"), which is more than most definitions offer. However, it states no exclusions and does not say when to prefer race_odds or market_pulse over this tool, so the routing decision is left partly to inference.

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