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

There are no annotations, so the description must carry behavioral disclosure. It reveals that the reading list is 'in-memory' (implying transient state) and that the tool operates on a 'named' collection. However, it does not disclose whether adding a duplicate paper overwrites or appends, what happens when a collection doesn't exist, or what the return value indicates. With 9 parameters and no annotations, more behavioral detail would help, but the 'in-memory' and 'reuse' hints provide some transparency.

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 three sentences, with the main purpose front-loaded. Each sentence contributes: the first states what it does, the second explains input modes, and the third gives usage advice on collections. There is no fluff or repetition; it is appropriately concise and well-structured.

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 9 parameters, no schema descriptions, no annotations, but an output schema is present, the description covers the core semantics well. It explains the three input modes and the collection reuse pattern, which are the most critical aspects for correct usage. It does not explain the 'engines' parameter or return value details, but the output schema may cover returns. For a comprehensive tool like this, the description is complete enough for most usage scenarios, though some parameters remain under-specified.

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 compensate. It explains the three ways to specify a paper: paper_json, DOI, query+result_index, and author_name+candidate_index+paper_index. This directly maps to the schema's parameters and explains their combined meaning. It also clarifies the 'collection' parameter's purpose via 'Reuse the same collection name.' However, the 'engines' parameter remains unexplained, and the exact format of paper_json is only hinted at ('copied from another ScholarFetch tool result'). Still, the description adds significant semantic value over the bare schema.

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 action: 'Add one paper to a named in-memory reading list on the MCP server.' The verb 'Add' and resource 'paper to reading list' specify exactly what the tool does, and this distinguishes it from sibling tools like saved_remove, saved_clear, and saved_list. It also adds the 'in-memory' and 'named' qualifiers, which further clarify the tool's role.

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 concrete guidance on when to use it and how: 'Best input is paper_json copied from another ScholarFetch tool result, but DOI, query+result_index, or author_name+candidate_index+paper_index also work.' This explicitly outlines three alternative usage modes and prioritizes the recommended one. It also provides advice on the collection parameter ('Reuse the same collection name'). It doesn't explicitly contrast with sibling 'remove' or 'clear' tools, but the workflow context is clear enough.

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