process_manuscript

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

With no annotations provided, the description carries the full burden of disclosure. It describes the outputs (docx, bibtex, ris, processing report) and mentions caching behavior via cache_ttl_hours. It does not cover any destructive actions or authentication needs, but the tool is read-only on the input file, so this is acceptable.

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 but comprehensive, with a clear top-line summary, a bulleted list of supported formats, and an Args section. Every sentence adds value; there is no redundancy 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 moderate complexity (7 parameters), the description adequately covers input format, parameters, and return value. The return value is described as a dict, but since an output schema exists (though not shown), the description need not detail it further. Minor missing details like error handling prevent 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?

Schema description coverage is 0%, so the description must fully explain parameters. It provides a detailed Args list for each parameter, explaining their purpose with examples (citation_style options, output format flags, cache TTL meaning). This adds substantial value beyond the schema structure.

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 'Process a Markdown manuscript with citation placeholders and generate formatted outputs.' This clearly identifies the specific verb (process), resource (Markdown manuscript), and action (generate formatted outputs). It distinguishes from sibling tools which are primarily download/read/search operations.

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 lists supported placeholder formats, giving users clear input expectations. Although it does not explicitly state when not to use this tool or name alternatives, the sibling tools are all for paper retrieval or cache management, so the unique purpose is evident. The lack of explicit exclusion is minor but prevents a score of 5.

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