Wiki Private Law

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

Even though annotations already declare readOnly, idempotent, and non-destructive behavior, the description adds significant transparency: answers are extracted verbatim, never generated, always include the URL, and return confident=false with suggested reading on out-of-corpus questions. This goes well beyond the annotations to clarify the tool's internal behavior and output semantics.

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 focused sentences, each adding meaningful information. The main action is front-loaded, followed by key behavioral details and language guidance. No filler or redundant repetition of schema content.

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 an output schema, clear annotations, and a description that explains the core behavior, error/fallback behavior, and language handling. For a Q&A tool, this is fully sufficient for an agent to select and invoke it correctly, even without seeing the output schema details.

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 well-documented. The description adds extra meaning by explaining that 'locale' dictates the answer language and that Russian and English are first-class, plus that locale is inferred when omitted. This supplements the schema with practical usage nuance.

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 answers a question by quoting a published wiki article, with a specific verb ('Answer') and resource ('published wiki article'). It distinguishes itself from generation-based answers by emphasizing verbatim extraction, which differentiates it from a generic search or Q&A 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?

The description gives some usage context (ask in the language you want answered, returns confident=false when corpus doesn't cover the question) but does not explicitly contrast with the sibling 'search' tool or state when to use one over the other. It implies usage by describing behavior but lacks explicit alternative 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds that results are 'ranked' and includes 'titles and URLs,' which gives useful context about the return format. However, it does not disclose behaviors like pagination, locale handling, or the meaning of 'published,' so it meets the baseline with annotations but does not go beyond.

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, front-loaded with the core action and followed by usage guidance. Every word earns its place with 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?

Given the tool's simplicity, the presence of an output schema, and strong annotations, the description fully covers the core purpose and use case. It explains what the tool does, what it returns, and when to use it, leaving no critical gaps for an agent to invoke it effectively.

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 67%: 'query' and 'limit' have descriptions, and 'locale' has an enum. The tool description itself does not add parameter-specific meaning, but the schema already explains query and limit. With high schema coverage, a baseline of 3 is appropriate; the description does not need to compensate.

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 function: 'Rank published articles for a query and return them with titles and URLs.' This uses a specific verb ('rank'), specifies the resource ('published articles'), and describes the return value. It also distinguishes from the sibling 'ask' by noting it returns sources rather than a single answer.

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 explicit when-to-use guidance: 'Use when you want sources to read rather than a single answer.' This clearly contrasts with the sibling 'ask' tool, implying the alternative without naming it. It does not list explicit when-not-to-use conditions, but the context is clear enough for an agent to decide.

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