save_paper

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

No annotations are provided, so the description carries the full burden of disclosing side effects. 'Save' only implies a write to the library; it does not disclose behavior on duplicate papers, whether the paper is validated for required fields, whether existing entries are replaced or merged, or what outcome is returned on success/failure. There is an output schema present, but the description itself reveals almost no 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?

The description is a single front-loaded sentence with zero waste, appropriately sized for a one-parameter tool. It loses a point only because it is so terse that it borders on under-specification for a persistence operation.

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 simple save operation with an output schema present, the return format does not need explanation. However, the open paper parameter is entirely unexplained, and with no annotations or schema coverage the description leaves a meaningful gap: an agent cannot know what constitutes a valid or complete paper to save. The low complexity is the only thing preventing a score of 1.

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 the description does nothing to compensate. The only parameter, paper, is an open object (additionalProperties: true), yet the description never hints at what fields an agent should populate (title, authors, content, URL, metadata, etc.). With the schema being permissive, an agent has no guidance on constructing a valid paper object.

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 a specific verb (save) and resource (research paper) plus a destination (local research library), which is clear. It also distinguishes the tool from its purely read/transform siblings (search_papers, get_paper, summarize_paper, compare_papers), since saving is the only write-persist operation. It drops one point because 'research library' is somewhat vague about what the library is or where it lives.

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?

No guidance is given on when to use this tool versus alternatives such as list_saved_papers, search_saved_papers, or get_paper. Nothing states whether the paper should come from a prior search_papers/get_paper call, whether it overwrites on duplicate, or when a user should save vs. just retrieve. The usage context is only implied by the verb 'save'.

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