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

The description discloses the 'in-memory' nature and that it removes exactly one paper. But with no annotations, it does not address what happens when no matching paper is found, whether both DOI and title are provided, or whether removal is permanent (especially given the in-memory 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?

One sentence, tightly constructed with no filler. Verb, object, and method are all front-loaded.

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 gives a clear idea of the tool's function but leaves out edge cases. Since an output schema exists, return values are covered, but the description does not clarify required inputs (schema says all optional, while description implies DOI or title is needed) or behavior when the list or paper is missing.

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?

The schema has no per-parameter descriptions (0% coverage), but the description explains that doi and title serve as alternative identifiers and 'named' list corresponds to the collection parameter. It doesn't clarify that all parameters are optional or the default behavior, but adds significant meaning beyond 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 uses a specific verb ('Remove') and resource ('paper from a named in-memory reading list'), and clarifies the identification method ('by DOI or exact title'). It clearly distinguishes from sibling tools like saved_add, saved_clear, and saved_list.

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?

It clearly implies when to use: to remove a single paper from a specific in-memory collection. However, it does not explicitly mention alternatives or exclusions (e.g., use saved_clear to remove all papers) or explain prerequisites like the list must already exist.

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