Oncast

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

Annotations already cover read-only, open-world and non-destructive semantics, so the description correctly spends its words elsewhere: it itemizes exactly what comes back, which matters since no output schema exists. It omits failure behavior (unknown id) and any auth or rate caveats.

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 return-content enumeration is front-loaded and every listed field earns its place because no output schema carries that information; the final sentence doubles as an actionable instruction.

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 one fully described parameter, the description does the heavy lifting on return contents and does it well. The remaining gap is behavioral edge cases — what happens with a bad id or a nonexistent story — which an agent would still have to discover by calling.

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 'id' parameter is fully documented there, including the id-slug variant, so the description is not required to compensate. It adds nothing about the id, which is the correct baseline-3 posture.

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 — exactly one verified Oncast story — and enumerates its contents (summary, fact-check verdict, sources, host commentary, timestamps, URLs). The singularity plus the sibling names latest_stories/search_stories make the single-record vs. list distinction obvious 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?

Usage is only implied: the reader infers this is the fetch-by-id tool used after a search or listing surfaces an id. No sibling is named and no when-not-to-use guidance is given, though the closing instruction 'Cite the story URL and the sources' gives a downstream behavioral cue.

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, destructiveHint=false, and openWorldHint=true. The description adds useful behavioral context beyond that: only verdict-reached claims with original source links are included, every story carries source links and an oncast.fm URL, and both should be cited.

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 purpose and inclusion criteria, then covers citation expectations, the get_story alternative, and the broadcast clarification. Each sentence carries distinct, useful information with no waste.

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 full schema coverage, existing annotations, and no output schema, the description supplies enough context for correct invocation: inclusion criteria, expected source links/URL, citation requirement, and sibling routing. Nothing essential is missing 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 description coverage is 100%, so limit, topic, and channel are already documented in the input schema. The description adds no parameter-specific syntax or filtering details beyond the schema, making the baseline 3 appropriate.

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 resource — 'Latest fact-checked Oncast stories' — and defines inclusion criteria (verdict reached, original source link present). It also distinguishes the tool from get_story by directing host commentary there.

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 explicitly routes host-statement questions to get_story and clarifies that the tool does not start a broadcast. It does not explain when to use search_stories or list_channels, but the 'latest' framing gives clear context.

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, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds genuinely new expectation-setting by noting there are no listener counts and no internal settings, telling the agent what will not be returned, which is useful for a list 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?

Three short sentences, front-loaded with the purpose before the content details and the exclusions. Every sentence carries distinct information with no repetition of the schema 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?

For a zero-parameter, non-destructive read with no output schema, the description tells the agent what a channel record includes (listen URL) and what it excludes. It doesn't mention ordering or whether the list is exhaustive, but nothing essential to calling the tool correctly 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?

There are zero parameters, so per the rubric baseline is 4. The description correctly adds nothing about inputs, which matches the empty 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 uses a specific verb+resource ('List Oncast radio channels'), enumerates the content variants (English, Tech and Money in Mexican Spanish), and states what each item contains (the oncast.fm listen URL). The sibling tools all concern stories, so there is no ambiguity about which tool to pick.

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 by the verb 'List' and the channel resource, but there is no explicit statement of when to call this versus alternatives or any prerequisites. Given the siblings are story-focused and non-overlapping, the lack of explicit routing guidance is a minor, not critical, 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?

Annotations already declare this a non-destructive, open-world read, and the description adds real behavioral detail the annotations cannot: the indexes matched (titles, fact-check summaries, sources, host quotes), the presence of source links and an oncast.fm URL in each hit, and the expectation to cite both. Pagination and result-cap behavior are left unstated.

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, front-loaded with what is searched and what is matched, then the payload shape, then the citation rule. No filler and nothing buried.

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 search tool with no output schema, the description usefully characterizes the return (source links plus an oncast.fm URL) and the safety profile is covered by annotations. Minor gaps remain on result ordering, pagination, and how topic/channel interact with a free-text query.

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 four parameters are already documented, making 3 the baseline. The description contributes only the word "keyword" plus an implicit recency scope that has no corresponding schema parameter, 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?

"Search recent verified Oncast stories by keyword" gives a specific verb (search), resource (stories), and a qualifier (recent, verified, keyword) that separates it from a plain listing. It never names get_story or latest_stories explicitly, so the boundary with siblings is inferable but not stated.

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 rather than stated: keyword-driven discovery as opposed to fetching one story or browsing the latest. There is no explicit "use this when / not when" or pointer to latest_stories for browsing, though "Cite both" does give a post-retrieval usage rule.

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