gol24

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

Annotations only cover read-only and idempotency; the description adds substantial context beyond that: a 60 req/min rate limit, error behavior when the club is unknown (returns similar names to retry with), and the return payload shape. This is unusually rich for a read 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?

Front-loaded with the core purpose, then routing, matching rules, returns, error handling, and rate limit in a logical order. Six sentences is on the long side, but each carries routing or behavioral information that isn't redundant.

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 explains the return payload (matched club name, gol24.uz page, up to limit items) and the error/retry path plus rate limit. Nothing an agent needs to call or recover from this tool 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 coverage is 100%, so parameters are already documented; the description mostly echoes that. It does add one piece of operational semantics not in the schema: that an unknown club yields an error listing similar names which should be used to retry. Helpful but largely duplicative.

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?

Opens with a specific verb+resource+scope ('News about one football club from gol24.uz, newest first'), and explicitly distinguishes itself from search_news, person_news, and latest_news by naming each. An agent can route without opening any 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?

Gives explicit when-to-use ('whenever the question is about a specific club') with example queries, and when-not with the alternative for each case: person_news for a player/coach, latest_news for general news. Nothing is left to inference.

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 cover the safety profile (readOnly, idempotent), and the description goes well beyond them: rate limit (60 req/min), default and max result count, timezone semantics (Tashkent time), empty-list meaning, and the exact shape of returned fields. This is unusually rich behavioral context.

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-loads the core purpose, then sibling routing, then filters, then return shape and limits. Every sentence carries information an agent needs; no padding.

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?

No output schema exists, but the description compensates by enumerating returned fields, the empty-result case, the rate limit, and default limits. Nothing material to correct invocation 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 coverage is 100%, so parameters are already documented; the description mainly restates the type enum meanings. It does add genuine value by explaining that the filters can be combined, which the schema does not convey.

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+resource+scope ('most recent published news from gol24.uz, newest first') and explicitly differentiates itself from all three relevant siblings by naming the routing rule for each. An agent can select this tool without ambiguity.

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 concrete example phrasings of when to use it, then explicitly routes to alternatives: club_news for one club, person_news for one person, search_news for topic/keyword. When-to-use and when-to-use-something-else are both present.

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 only declare readOnlyHint and idempotentHint; the description goes well beyond them by disclosing the return shape (up to 20 related items, newest first, same fields as latest_news), the empty-'related' edge case, the error conditions (item missing or unpublished), and a concrete rate limit of 60 req/min.

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-loads what the tool returns, then usage routing, then input forms, then behavioral caveats. Every sentence carries distinct information with no 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?

With no output schema, the description compensates by describing the return payload, its ordering, its empty case, and its failure modes; combined with the rate limit and routing guidance, an agent has everything needed 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% and the schema description already covers id, url and slug, so the description largely restates the accepted input forms. It adds only the concrete URL pattern example, which is marginal over the schema. 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 (one gol24.uz news item plus its full story thread) and scope (related items newest first), which cleanly separates it from the sibling list/search tools that return single items. An agent can tell immediately that this is a story-expansion tool, not another feed.

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 to use it 'after latest_news, club_news, person_news or search_news returned an item and the user wants the background or follow-ups' — naming all four alternatives and the trigger condition. Nothing is left to inference.

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 only declare readOnlyHint and idempotentHint, but the description adds the rate limit (60 req/min), the error behavior on no match, the automatic English-to-Uzbek spelling matching, and the shape of the response (matched name plus up to `limit` items). That is substantive operational context beyond the 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?

Front-loaded with purpose and routing, and every sentence carries information (routing, spelling behavior, full-name requirement, return shape, error fallback, rate limit). It is slightly long, with several parenthetical examples that could be trimmed without loss.

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 explains what comes back (matched name plus items) and defers field details to latest_news, which requires cross-referencing a sibling rather than being self-contained. Error handling, rate limits, and input expectations are otherwise fully 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 100%, so the baseline is 3, but the description adds real meaning: it warns that a surname alone is usually not enough, shows Uzbek Latin vs English name forms, and explains that alternate spellings are matched automatically. The only reason it is not a 5 is that the limit bounds it restates are already 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?

States a specific verb+resource+scope ('News about one person ... from gol24.uz, newest first') and explicitly distinguishes itself from siblings search_news and club_news. An agent can select it without opening any 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?

Gives an explicit routing rule ('Use it instead of search_news whenever the question names a specific person. For a club use club_news') plus a failure-recovery path ('If nobody matches, returns an error - then try search_news with the surname'). Both when-to-use and what-to-do-on-failure are covered.

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 only cover readOnlyHint and idempotentHint; the description adds the real behavioral detail: matching is a case-insensitive substring on title and summary, scoped to the last `days` days, an empty list means no match, and there is a 60 req/min rate limit. It also warns that content is Uzbek Latin script, which materially affects success.

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 dense sentences, front-loaded with purpose and routing before mechanics. Every sentence carries unique information (routing, matching semantics, return shape/rate limit) with no 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?

For a search tool with no output schema, the description still tells the agent the return shape ('up to `limit` items with the same fields as latest_news') and the failure mode (empty list). Combined with the 100%-covered input schema, nothing needed to invoke or interpret it 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?

Schema description coverage is 100%, so the baseline is 3, but the description adds non-duplicative meaning: the substring/case-insensitivity semantics of `query`, the rationale for raising `days` ('increase it for older events'), and how to interpret an empty result. It largely restates the default/max values already in the schema, which caps it at 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?

States a specific verb+resource ('Keyword search in gol24.uz news titles and summaries') plus ordering ('newest first'). It explicitly differentiates itself from sibling tools club_news and person_news, so an agent can route without opening schemas.

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 when-to-use cases ('topics, events or names that club_news and person_news cannot resolve') with concrete examples, and an explicit when-not-to-use rule ('for one specific club or person prefer club_news / person_news - they are more precise'). This is a full routing rule.

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