Track Podcasts

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

With no annotations, the description carries the full burden and does well: it discloses ordering ('newest first'), a non-obvious truncation behavior ('the exact total even when the list itself is truncated for the plan'), and the degenerate-input outcome (candidate brands on ambiguity). It does not cover auth or rate limits, but the key behavioral surprises are surfaced.

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, each earning its place: purpose, return behavior, then input forms and the ambiguity fallback. Nothing is repeated from the title or schema verbatim.

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 must explain return values — it does so (matching shows, newest-first order, exact total, plan-based truncation, candidate-brand fallback). For a single-parameter read tool this is everything an agent needs 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 baseline is 3; the description earns above that by adding that domains are the most reliable form and that an ambiguous name yields candidate brands rather than a failure. That is decision-relevant meaning the schema does not carry.

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 ('Which podcasts a brand advertises on') plus the scope of what's returned ('shows where that brand's ad reads were detected'). The direction of the relationship (brand → shows) is unambiguous and implicitly opposite to get_show_sponsors, so an agent can route correctly.

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 clear usage context for the input ('accepts a brand name, slug or domain') with a preference ranking ('a domain is the most reliable'), and defines fallback behavior ('returns candidate brands when the name is ambiguous'). It never names a sibling as an alternative for cases where the agent actually wants show→brand data, so it stops short of full when-to-use/when-not 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?

With no annotations present, the description carries the full burden and does well: it defines the ranking metric (ad reads detected), states the two accompanying fields (brand count, show count), and explicitly bounds the output as aggregate-only. It does not say how many categories are returned or whether the list is truncated to a top-N, which is the remaining behavioral gap.

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 metric and ranking come first, the scope boundary second. Every clause carries information an agent needs.

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 one-parameter, no-output-schema, read-only aggregate tool, the description covers what is ranked, by what metric, and what is excluded — enough to invoke it correctly. Only the result-set size/ordering remains unspecified, which is minor at this complexity.

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 `days` parameter already documents its enum values and 30-day default. The description adds no interpretation of the lookback window, 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 ranking operation over a specific resource: advertiser categories ranked by ad reads detected, with brand and show counts. The closing clause 'Aggregate only — it does not list the brands in a category' explicitly separates it from the brand- and show-level siblings, so no schema inspection is needed to tell them apart.

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?

'Buying the most podcast ads right now' plus 'Aggregate only' gives a clear condition for selection and an implicit exclusion of brand-detail lookups. It stops short of naming the alternative tool (e.g. get_brand_podcasts) for the per-brand case, leaving that inference to the agent.

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?

No annotations are provided, so the description carries the full burden. It discloses that the tool returns coverage/perimeter metadata rather than findings, and warns of incompleteness by design. It stops short of saying whether results are cached, how fresh they are, or whether counts are approximate.

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: first defines what is returned, second gives the calling condition. Front-loaded and waste-free, though a slightly more explicit link to the sibling data tools could be fitted without bloat.

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-param, no-annotation metadata tool, the description covers purpose and calling conditions well. With no output schema, it could say more about the shape of the response (counts vs percentages), which is the one real gap.

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?

Zero-parameter tool, which is the baseline-4 case. The description needs no parameter explanation, though it could note that coverage is global and cannot be scoped to a single brand or show, which matters if a caller wants per-entity percentages.

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 resource (dataset coverage) and enumerates what it reports: shows indexed, episodes transcribed, brand and show counts with detected ad reads. Clearly distinct from data-returning siblings like get_brand_podcasts.

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 says when to call it ('before stating any sponsor finding as complete') and what it's for ('explain why a show or brand might be missing'). That's a named precondition plus a diagnostic use case, with no ambiguity.

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?

With no annotations, the description carries the disclosure burden and does well: it explains the returned fields, ambiguity behavior, and inclusion criteria. It does not discuss permissions, rate limits, or error behavior, which keeps it below the highest level for a no-annotation tool.

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 purpose and then adds only useful details: return contents, accepted input forms, ambiguity handling, and inclusion criteria. Every sentence contributes without repetition.

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 one-parameter read tool with no annotations or output schema, the description provides enough detail about inputs, returned data, ambiguity handling, and exclusions for an agent 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 coverage is 100%, so the schema already documents the single show parameter. The description adds meaningful semantics beyond the schema by clarifying accepted title/slug/URL forms and the ambiguity-resolution behavior.

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 query: who sponsors a given podcast, returning every brand whose ad read was detected. It clearly distinguishes detected ad reads from mere mentions, but it does not explicitly differentiate this show-to-brand lookup from the sibling get_brand_podcasts tool.

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 clear use context and an exclusion: detected ad reads only, not brands merely mentioned. It also explains ambiguity handling by returning candidate shows rather than guessing, though it does not explicitly name the sibling alternative for reverse brand-to-podcast lookup.

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?

No annotations exist, so the description carries the full burden, and it does disclose the 36-month ceiling plus the important interpretive caveat that zero-filled months mean 'not detected', not 'stopped advertising'. It omits operational traits such as permissions, rate limits, and latency.

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: the resource and metrics first, the use case second, the interpretation caveat last. No filler and the most decision-relevant facts are 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?

With no output schema, the description still names the returned dimensions (shows, ad reads, organic mentions, month by month) and the zero-fill convention, which is enough to interpret results. A brief note on how trends are ordered or bounded by available data would close the remaining gap.

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 both parameters are documented there (brand as name/slug/domain, months default 12, max 36). The description only echoes the 36-month cap without adding format or parsing guidance, so 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 resource (a brand's podcast advertising) and the exact metrics returned (shows reached, ad reads, organic mentions) at monthly granularity. That detail implicitly separates it from get_brand_podcasts and get_show_sponsors, but it never names or explicitly contrasts with a sibling.

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 a clear use context with two concrete example questions ("is this brand spending more?", "when did they start?"), which tells the agent this is the trend/history tool. It stops short of naming an alternative tool or stating when not to use it.

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