broadcast

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

With no annotations provided, the description carries the burden of behavioral disclosure. It does reveal that results include closure dates and that the tool is useful for existence checks, implying that if a channel appears here it no longer exists. It does not mention query matching behavior, limit semantics, ordering, or whether the list is exhaustive, but for a presumably read-only lookup the provided info is minimally adequate.

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 short and front-loaded, with the core information in the first sentence and the use case in the second. Both sentences add value and there is no filler. It could be improved by adding an explicit verb, but as written it is efficient and well-structured.

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?

The tool has no output schema, no annotations, and zero parameter documentation, so the description must provide enough for correct invocation. It explains the domain and one use case but leaves parameter semantics and expected results undocumented. An agent cannot confidently craft a correct query or interpret results, making the description incomplete for a 2-parameter 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%, so the description is the only place to explain 'limit' and 'query', yet it says nothing about either parameter. The agent is left to guess whether query is a search term, exact name, or pattern, and what limit controls. This is a significant gap with two parameters and no schema documentation.

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 identifies the resource as 'channels that have shut down' and adds the closure date, making the core purpose understandable. It also ties the tool to a concrete use case (checking whether a remembered channel still exists), which distinguishes it from siblings like media_still_true. It lacks an explicit verb ('List' or 'Get'), but the meaning is clear enough.

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 one usage context: checking whether a channel a model remembers still exists. However, it does not name sibling tools or state when not to use this tool, nor does it explain how it relates to alternatives like media_verify or media_still_true. The guidance is implied rather than explicit.

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 burden of behavioral disclosure, and it does communicate the informational scope: source run time, live/expired counts, and known gaps. It does not explicitly say whether the operation is read-only, cached, or triggers any computation, but the phrasing strongly implies a non-mutating status report.

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?

One tight, front-loaded sentence conveys the main idea and the key contents in a colon-delimited list. There is no filler text, though an explicit verb and parameter mention would strengthen it.

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?

The description gives a helpful high-level summary of the return contents, but with no output schema and no mention of the query parameter, an agent lacks enough detail to construct a fully informed call. It also provides no guidance on how this tool compares with the many siblings.

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 only parameter, query, is a bare string with zero schema description, and the tool description never mentions it. At 0% schema coverage, the description was expected to compensate but offers no detail on expected values or whether the parameter filters or selects.

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 opens with 'How current this dataset is,' which clearly frames a freshness/status reportaine, and then lists concrete contents: when each source last ran, live vs expired assertions, and known gaps. It distinguishes itself from sibling tools by topic even though it lacks an explicit verb such as 'show' or 'get'.

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?

No sentence explains when to prefer this tool over siblings like media_still_true or media_verify, and no conditions or exclusions are provided. The description only implies that it should be used for dataset-currentness questions.

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 provided, the description carries the full burden of disclosing behavior. It mentions return fields (licence status, transmitter power, antenna height) but does not explicitly state that the operation is read-only, whether any permissions are required, rate limits, or potential side effects. It lacks critical behavioral context for an 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 a single, front-loaded sentence with no extraneous words. It efficiently communicates the core purpose and return highlights, making good use of space.

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?

Given the absence of an output schema and partial parameter descriptions, the description is incomplete. It doesn't explain how parameters interact, default behaviors, pagination, or the structure of the returned data beyond enumerating a few fields. An agent calling this tool would lack essential context for correct invocation and result interpretation.

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 50% (kind and region have descriptions; query and limit do not). The description adds no parameter semantics—it does not explain the expected format of query, the meaning or default of limit, or valid values for kind and region. It fails to compensate for the incomplete 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 clear verb 'Search' with specific resources ('stations, networks and streaming channels') and search criteria ('name, callsign, network or owner'). It also indicates what it returns, making the tool's purpose unambiguous and distinct from sibling tools like media_whats_on or media_verify.

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 provides no guidance on when to use this tool versus althernatives. It does not state exclusion criteria, alternative tools, or conditions under which another media_* tool should be preferred. Sibling tool names suggest their scopes but no explicit routing is given.

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 behavioral disclosure burden and does communicate the key behavior of using real terrain rather than simple coverage assumptions. However, it does not disclose output format, result ordering, or assumptions such as which transmitter classes are included by default.

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 with no filler; the core mechanism and question answered are front-loaded. Every clause earns its place and the second sentence usefully frames the value proposition.

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 six-parameter tool with no output schema and no annotations, the description leaves out the return shape, the role of full_power_only, and how this differs from sibling tools like media_whats_on or media_station_readiness. It is a strong pitch but not a complete calling contract.

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 description adds conceptual meaning for location and terrain, but it does not explain full_power_only, which also lacks a schema description. With only 50% schema description coverage, the missing full_power_only semantics and implicit coordinate/query handling are material gaps.

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 opening sentence names the exact query and method: which television transmitters reach a given latitude/longitude, graded by real terrain. It clearly distinguishes the tool from generic listings services, but it does not explicitly differentiate among the sibling media_* tools by name.

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 a clear use case: answer 'what can I actually watch from here' for physical over-the-air reception. The contrast with listings services signals when this tool is relevant versus a listing-oriented query, though it stops short of naming a concrete alternative or explicit when-not-to-use 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does not state whether this is a read-only operation, what the return format is, any side effects, or authentication requirements. The description only hints at the data content, not the tool's 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?

The description is a single short sentence with no fluff. It is concise to the point of being terse, but it does not waste words. However, the brevity comes at the cost of necessary information, so the structure is acceptable but not exemplary.

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?

Even though the tool is simple (one parameter, no output schema), the description is far from complete. It does not explain what 'data' refers to, what a 'media source' is, what the query does, or how the response is structured. With multiple siblings covering related media concepts, the lack of differentiation and usage context makes the description inadequate for any real agent.

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 schema has one optional 'query' string parameter with 0% coverage in the description. The description does not explain the purpose or format of the query parameter, nor how it filters the results. For an agent to use it correctly, the description must compensate for the schema's lack of description, and it fails completely.

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 the domain (media sources) and the kind of information (licence, redistribution), but lacks an explicit verb like 'list' or 'retrieve'. It is distinguishable from siblings by name but not through any active phrasing. It gives a vague purpose that an agent could infer but not rely on.

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?

No guidance is provided on when to use this tool versus siblings like media_outlets or media_verify. There is no mention of prerequisites, context, or exclusions. An agent must guess the scope from the name alone.

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 provided, the description does carry the burden of disclosing behavior. It explains the specific checks performed (robots.txt, llms.txt, /.well-known/ai, structured data) and the two modes (single station vs. industry summary). However, it omits potential outcomes like error behavior for unknown callsigns, rate limits, or return format, which prevents a higher score.

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 a single dense sentence that packs in a lot of information, but its structure is slightly confusing: the list of checks is appropriate, yet the parameter instructions ('Pass a callsign') are vague and not front-loaded with a clear hierarchy. It could be split into two sentences for better readability, and the parameter guidance is insufficient.

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 tool with no annotations, no output schema, and two parameters (one undocumented), the description is incomplete. It explains what data is gathered but not how results are returned (format, structure), how to interpret the summary, or how errors are handled. Combined with the parameter ambiguity, an agent would struggle to invoke it correctly without more information.

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 50% (query has a description, callsign does not). The tool description says 'Pass a callsign' but does not clarify whether to use the 'query' or 'callsign' parameter, and the free-text option for 'query' is not reconciled with the callsign field. This ambiguity adds no value beyond the schema and fails to compensate for the missing callsign description.

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 clearly states the tool's purpose: determining whether a US TV station website is readable by AI assistants, with specific checks (robots.txt, llms.txt, structured data). It is specific and informative, though it doesn't explicitly differentiate from sibling tools like media_closed or media_verify, so a perfect score is not warranted.

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 input guidance (pass a callsign or nothing for summary) but no guidance on when to choose this tool over the many siblings in the media_* family. There is no comparison or alternative mentioned, leaving selection to inference. This is a significant gap.

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 full burden. It discloses key behavioral outputs: when the claim was observed, whether it expired, and what replaced it. However, it does not state whether the operation is read-only, how expiry is determined, or what data source is consulted, leaving meaningful gaps.

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 compact and front-loaded with the core question, then quickly lists the return information. The final sentence about training data adds useful context rather than padding. Slightly more structure around parameter expectations would improve it, but no words are wasted.

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?

The core purpose and primary returns are clear, and the tool appears simple. However, with no output schema, no annotation safety profile, and no explanation of `outlet` or expiry semantics, an agent lacks some details needed for robust invocation. It is adequate but not fully complete.

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 50%; `query` is described but `outlet` has no description. The tool description does not explain `outlet` or clarify how it relates to the query, so it fails to compensate for the undocumented parameter. It mostly restates what the schema already says about `query`.

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 operation: checking whether a remembered claim about a programme is still current, and it names concrete return content (observation time, expiry status, replacement). It does not explicitly contrast sibling tools like media_freshness or media_verify, but the 'model training data' framing makes the purpose fairly distinctive.

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?

Usage is implied through the question 'Is a remembered claim about a programme still current?' and the note about a model's training data, but there are no explicit when-to-use or when-not-to-use instructions and no alternatives are named. An agent can infer context but gets no routing 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?

No annotations are provided, so the description carries the full burden. It discloses that the tool confirms byte-identical match and points to public key and canonicalisation for offline verification, which is helpful. However, it doesn't state side effects (e.g., whether it's read-only) or error behavior (e.g., what happens if signature mismatches), leaving some transparency gaps.

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 concise, two sentences, and front-loads the core purpose. It includes useful additional context (offline verification) without unnecessary fluff. It could be slightly more structured (e.g., bullet points for parameters), but current format is efficient.

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?

Given the complexity (5 params, nested objects) and no output schema, the description provides sufficient context for an agent to call the tool: how to construct the query, what the tool does, and how to verify offline. However, it doesn't describe the return format or error handling, which could be important for agents, but the core usage is covered.

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 80%, and the description adds meaning by explaining how parameters are used: passing an airing_id or a record plus signature. It also clarifies that query is free text and airing_id is picked out if present. This adds value beyond the schema, but for parameters like record_type (defaulting to 'airing') it doesn't explain implications, leaving some semantics to 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 clearly states the tool verifies a signed record and provides two usage modes: passing an airing_id or passing a cached record with its signature. It distinguishes from siblings by focusing on verification, which is unique among the listed media tools, though it doesn't explicitly name a sibling to differentiate from.

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 explicit instructions on when to use the tool: either with an airing_id or with a previously cached record and signature. It also mentions an offline alternative, which guides the agent on when not to call this service. However, it doesn't explicitly state when this tool is preferred over siblings, but the context of verification is clear.

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 present, so the description carries the behavioral disclosure burden. It usefully reveals the output shape: programmes with descriptions and claim observation/expiry timestamps. However, it does not mention permissions, data freshness semantics, rate limits, or any side effects, so coverage is adequate but not rich.

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 tightly worded sentences with the core purpose front-loaded. Every clause adds information: time scope, response contents, observation/expiry timestamps, and free-text acceptance. There is no repetition or 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?

The description covers the essential purpose and return shape, which is helpful given there is no output schema and no annotations. Still, an agent is left without details on how 'claim observed/expires' should be interpreted, what 'limit' means, and how this tool differs from semantically adjacent siblings. Adequate but not complete.

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 75%, and the description reinforces that query is free text and that time-based lookup is supported. Yet it adds no meaning for 'limit', which is undocumented in both the schema and the description, and it provides no additional nuance for 'outlet' beyond 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 opens with a clear, specific question ('What is airing right now, or at a given time') and explicitly states that it returns programmes with descriptions, observation time, and expiry time. This clearly identifies the resource and action. However, it does not explicitly contrast with sibling tools like media_verify or media_still_true, 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?

The description implies use for current or time-specific programme lookup and notes that it accepts free text, which gives some situational context. But it never states when not to use it or names alternatives among the eight siblings, leaving selection guidance to inference.

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