jstage_search_articles

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

Annotations already provide readOnlyHint and idempotentHint, but the description adds substantial behavioral detail: full-text matching with loose multi-word handling, the need to read matching_mode and result.breadth, the SCRIPT_LATIN_QUERY diagnostic meaning and remediation, and the cross-database variation with CiNii. This goes well beyond the annotations and sets clear expectations about query semantics and result interpretation.

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 concise (two paragraphs) and front-loaded with the purpose. It arranges critical caveats in a logical flow, with the first sentence stating the action and the following sentences providing necessary warnings. No fluff, but it could be slightly more compact without losing nuance.

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 has 14 parameters and an output schema, the description focuses heavily on the behavior of the `text` search and result interpretation. It does not cover how to combine filters, pagination semantics beyond what the schema implies, or potential rate limits. The presence of an output schema reduces the need to explain return structure, but the description still lacks guidance on parameter interplay and tool-specific constraints.

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 0% and parameter descriptions in the schema are minimal (e.g., 'Issue filter'). The description adds meaning primarily to the `text` parameter (full-text matching, loose terms) and implicitly references result.total, but other parameters like no, vol, pubyearfrom, etc., are not explained. The description does not compensate adequately for the lack of coverage across the many filters.

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 'Search articles on J-STAGE', a specific verb and resource. It clearly distinguishes itself from sibling tools jstage_get_article_by_doi (retrieval by DOI) and jstage_list_issues (listing issues). The mention of 'Returns the unified response envelope' further clarifies the action 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?

The description gives guidance on interpreting results (noisy totals, SCRIPT_LATIN_QUERY re-issue in kanji/kana) and contrasts with CiNii behavior, but does not explicitly state when to use this search tool versus fetching a specific article or listing issues. The when-to-use context is implied by the tool's purpose but not explicitly articulated.

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