TheRundown Data MCP

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely new context: retrieved_at is not price freshness, and each local page is metered (a cost/rate constraint not visible in annotations). The 'preserves participant identity, line value and price updated_at' sentence overlaps the output schema, so it is slightly redundant rather than additive.

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 action, then the gating precondition, then caveats and cost note. Every sentence carries operational weight except the 'preserves ...' line, which restates output-schema content and could be dropped.

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?

An output schema exists, so return values need not be explained, yet the description does so anyway (mild redundancy). For a metered, ID-gated read tool with five parameters, the description covers invocation preconditions, cost, and market selection well; only page/limit behavior is 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 coverage is 60%, and the description reinforces the key semantic gap: market_ids defaults to prematch 1/2/3, so live data requires explicitly requesting 41/42/43, and event_id must come from list_events rather than a URL. It adds operational meaning over the schema, though it says nothing about page/limit tuning.

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 (Fetch) and resource (open per-affiliate main lines) plus the exact scope (one event_id). An agent can immediately tell this apart from the list_* discovery siblings, which enumerate rather than retrieve lines for a known event.

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?

Explicit precondition: 'Do not call until list_events returned that exact ID' names the alternative tool and the condition that gates this one. It also gives an override instruction for live markets (41/42/43), so the agent knows how to change behavior rather than relying on the prematch default.

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, idempotentHint, destructiveHint=false, openWorldHint), so the description only needs to add what they don't say. It does: the result set is limited to currently published affiliates with retired entries filtered out, and it warns that a catalog row does not imply plan access or an open offer — meaningful semantic context beyond the annotations. It stops short of noting ordering, freshness, or result size.

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, no filler. The concrete behavior (what is listed, what is excluded) is front-loaded, and the cautionary note follows only after the core purpose is established.

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 covering safety and idempotency, the description carries little remaining burden — and it meets it by defining scope and the correct interpretation of results. Minor omissions (ordering, pagination, or volume of affiliates) are the only reason this isn't a 5.

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 the baseline is 4 by rule; there are no parameter semantics for the description to clarify. Nothing in the description misrepresents the (empty) input contract, and it helpfully clarifies the implicit output scope instead.

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 ('List') and resource ('affiliate IDs and names') with an explicit scope qualifier: currently published, retired ones excluded. An agent can separate this from sibling catalog tools like list_sports or list_markets without opening any schema, and it even discloses which fields are returned.

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?

The description gives an interpretation caveat ('Do not use a catalog row as proof of plan access or an open offer'), which is useful guidance about the meaning of results. However, it never says when to prefer this tool over the sibling list_* tools, nor does it name any alternative or exclusion condition for tool selection. Usage is therefore implied rather than directed.

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 openWorld, so the safety profile is covered. The description adds real behavioral context beyond them: default market/affiliate selections and the important note that each page refetch hits a metered snapshot, which implies request cost. It stops short of stating rate limits or pagination semantics.

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 tightly packed sentences with no filler, ordered from purpose to exclusions to defaults/behavior. The critical routing constraint is front-loaded ahead of the defaults.

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 an output schema present, return format need not be explained, and annotations cover safety. The description supplies the routing and cost context an agent needs for a 7-parameter tool, though a few unmentioned parameters (page/limit/offset) are left solely 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 coverage is 57%, above the baseline threshold, and the schema documents date, offset, market_ids and affiliate_ids in detail. The description restates default values (1/2/3 and 19/23) already present in the schema and says nothing about page, limit, offset or sport_id, so it adds little beyond the structured fields.

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 ('Find event IDs and summaries') plus its scope ('for one sport and date'), which is exactly the identity an agent needs. It also distinguishes itself from siblings by naming get_main_lines as the downstream consumer of the returned IDs.

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 exclusions ('Do not use this tool for futures or as a price quote') and names the correct alternative pattern ('use the returned exact event ID with get_main_lines'). This is a clear when-to-use / when-not-to-use / what-else routing 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?

Annotations already cover readOnly/idempotent/non-destructive/openWorld, but the description adds real behavioral context beyond them: a plan-tier eligibility gate (Ultra or higher), opaque cursor pagination, and a warning that a partial page must not be treated as a full listing. These are non-obvious operational traits.

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, all front-loaded: scope first, then exclusions, then plan/pagination constraints. No filler, every sentence carries a distinct constraint.

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 an output schema present, return values need not be explained, and the description covers scope, exclusions, plan gating, and pagination. The remaining gap is per-parameter semantics for the four undocumented parameters, which is minor but not fully closed.

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 only 33%; only market_ids and affiliate_ids carry inline descriptions. The description mentions cursor pagination but adds no meaning for sport_id, limit, include_settled, or the semantics of cursor values, so it fails to compensate for the coverage gap.

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 ('read one sport's scoped futures competition page'), which is concrete and distinguishes the tool's domain from generic listing. It implicitly separates itself from dated-event tools by calling out 'dated event discovery', though it doesn't name the sibling (list_events) directly.

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 states when NOT to use it ('Do not use this for dated event discovery') and adds two further caveats: partial pages are not complete listings, and futures require an eligible Ultra plan. This is concrete when/when-not guidance not derivable from the schema.

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/openWorld safety, so the bar is lower, and the description adds two genuine behavioral constraints: definitions are not price quotes, and live cannot be combined with date-based discovery. It omits pagination behavior and response shape, and the closing 'catalog metadata' sentence is jargon that resists interpretation.

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 compact sentences with the core capability front-loaded and constraints following. No wasted filler, but the final sentence is dense jargon-heavy shorthand that would benefit from one clarifying clause.

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?

An output schema exists so return values need not be explained. However, with 0 required params, 17% schema coverage, and no enum for sport_id or explanation of the pagination-vs-time-offset distinction, the description leaves an agent guessing about valid inputs and mutual exclusivity of live/date.

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 only 17% across 6 params, so the description must compensate. It implies date, sport_id, and live are mutually constrained (one sport, one date, live vs. date-based), but it says nothing about page/limit/offset semantics — and 'offset' here is a minutes-based date boundary, not pagination, an ambiguity the description does not resolve.

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 ('Discover') and resource (market definitions / available markets) and distinguishes two modes: definitions vs. sport/date-scoped availability. It does not name or contrast itself against any sibling tool such as list_sports or list_events, so it stops short of a 5.

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 real when-not guidance: do not use definitions as price quotes, and do not combine live with date-based discovery. It also points to catalog metadata for sport/live filters. It never names an alternative tool to use instead, so it falls 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=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered by structured data. The description adds that the returned IDs/names are static catalog metadata not tied to live events/prices, which is genuinely useful context beyond annotations but limited in depth.

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 short sentences with zero waste; the primary purpose is front-loaded and the caveat follows efficiently.

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 an output schema available, the description needn't explain return values. Combined with annotations and full schema coverage, it is complete enough for an agent to call this zero-arg list tool, though it could more explicitly position itself against sibling listing tools.

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 the baseline is 4. The description correctly implies no filtering arguments are needed.

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 ('List') and resource ('current canonical sport IDs and names'), making the scope and output explicit. It is clearly distinguishable from siblings like list_events or list_markets, which cover different resources.

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 a caution ('Do not use a catalog row as evidence of current events, prices, or plan access') that governs downstream usage, but gives no when-to-use guidance relative to alternatives such as list_events or get_main_lines.

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