MediaWiki

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

The description richly discloses behavioral traits beyond the readOnlyHint annotation: case-insensitivity, no stemming, silent dropping of punctuation, character n-gram indexing for CJK scripts, URL-priority over wiki=, dispatcher rejection of mismatched parameters, and the behavior of search operators. This provides deep insight into how the tool executes, which annotations alone do not convey.

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 long but well-structured with clear sections (Actions, PARAMETER SPLIT, Query formats, search= operators, Wiki instance). It is front-loaded with the primary purpose. However, the extensive operator details and lengthy examples could be trimmed; some sentences are redundant with the schema (e.g., action descriptions). Overall, it earns a slightly above-average score for organization but loses points for verbosity.

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 is extremely thorough on input semantics, covering all parameters, edge cases, and operator syntax. However, with no output schema, it does not describe the structure of the returned content (e.g., what fields are present in a page fetch or search result). This is a notable gap for a tool with multiple actions and no return type documentation, keeping it from a perfect score.

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?

Even though schema coverage is 100%, the description adds substantial meaning: it explains the title/query split, the distinct meanings of 'search' (within-page) vs query (full-text), the footnotes/citations formats, and detailed query syntax. For example, it clarifies that 'search=' uses tantivy query language while 'query=' supports MediaWiki operators, which is not apparent from the schema alone.

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 and resource: 'Search and retrieve content from Wikipedia and other MediaWiki sites.' It clearly distinguishes from siblings by noting it avoids web_search with site: filters and that web_fetch_incisive handles URLs automatically. The action list (page, search, references) further clarifies the scope.

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?

Explicit guidance is provided: 'Use this for direct Wikipedia access without resorting to web_search with site: filters.' It also mentions when web_fetch_incisive is the appropriate alternative for URL handling. The parameter-split explanation ('PARAMETER SPLIT') tells the agent exactly which parameters to use for each action, preventing misuse.

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