RSS and news feeds for agents

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

Beyond the read-only and idempotent annotations, the description discloses the actual search strategy: alternate tags, Link header, feed-shaped links, common paths, legacy feeds, and the order of attempts. It also states that every tried rung is returned, giving agents useful expectations about output completeness.

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 dense but information-packed, with the tool purpose front-loaded and usage guidance at the end. No sentence is wasted, though the long semicolon-heavy sentence could be restructured for easier parsing.

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 no output schema, the description usefully explains the discovery algorithm, the cost-related option, and the situations in which the tool should be invoked. It could be slightly more explicit about the exact shape of the returned result, but nothing critical 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?

Schema description coverage is 100%, so the schema already documents site, task_context, and all. The description adds no meaningful parameter-level semantics beyond the schema, making the baseline score of 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 opens with the specific verb 'Find' and a precise resource ('RSS/Atom/JSON feed(s) of a site'), then enumerates the discovery techniques used. It also distinguishes itself from the feed_items sibling by mentioning 'feed_items missed', making the tool's role clear.

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 tool explicitly states when to use it: when you need a feed URL, want all feeds from a site, or need to debug why feed_items missed something. It does not explicitly contrast with news_search, so it lacks a full when-not-to-use boundary, but the provided conditions are 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?

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description discloses meaningful behavioral details: newest-first ordering, deduplication, optional date filtering, bounded plain text, and the discovery ladder when given a site URL. It also reveals that the result reports how the URL resolved, which is useful for agent interpretation. No contradiction with annotations.

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 sentences deliver a complete mental model: what is returned, how items are ordered and filtered, URL flexibility and resolution reporting, and the intended use case. Every clause earns its place; there is no repetition of schema defaults or annotation trivia.

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 compensates by enumerating the returned fields and noting the resolution message. It covers the main parameters (url, since, task_context, bounded text) and the tool's behavior. The only small gap is that 'limit' is not mentioned in the description, but its schema default and bounds make it fairly self-explanatory.

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%, so the baseline is 3. The description adds real value beyond the schema: it explains that url may be a feed URL or a site undergoing discovery, that 'since' filters by published or updated date, that text is bounded, and that task_context tunes the result. This goes beyond the schema's individual descriptions, justifying a 4.

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 specific verb ('Read') and resource ('a feed'), then enumerates the exact output shape (id, title, url, published, authors, categories, lead, plain text). It also states ordering and deduplication, making the tool's purpose unmistakable and implicitly distinguishing it from siblings like feed_find and news_search.

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 final sentence, 'Use for "what is new on X"', is a clear trigger for when to invoke this tool. It also explains that url can be a feed URL or a site URL, so the discovery behavior is contextualized. It does not explicitly contrast with siblings or state when not to use it, 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?

With no output schema, the description carries the burden of explaining return behavior, and it does so richly: results are fused by reciprocal rank, deduplicated by normalized URL, grouped under also_on, and tagged with publisher and source engines. It also discloses that the service is keyless and that task_context tunes results, which goes well beyond the readOnlyHint and destructiveHint annotations.

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 two sentences with no filler. The first sentence packs every meaningful behavioral detail into a compact list, and the second sentence immediately tells the agent when to use an alternative.

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, the description fully compensates by explaining sources, result structure, deduplication, grouping, and provenance signals. It also covers usage context and keyless access, making it sufficiently complete for an agent to invoke the tool 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 high at 83%, so the schema already documents most parameters. The description adds little parameter-level detail beyond the schema's own descriptions, and the one undocumented parameter, limit, still has clear min/max/default constraints in 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 states a specific verb and resource: it is a news search fusing Google News RSS and Bing News RSS. It goes beyond the tool name by explaining the fusion, deduplication, and grouping behavior, and it explicitly distinguishes itself from feed_items for single-site post retrieval.

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 says to use this tool for 'what is the news about X' and routes single-site post needs to feed_items. This gives an agent a clear decision rule between the search tool and a sibling, though feed_find is not directly addressed.

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