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

Annotations already declare readOnlyHint, idempotentHint and that nothing is destroyed, so the safety profile is covered. The description adds genuinely new behavioral context: results come back a page at a time and the response includes nextCursor for continuing, which is the paging contract an agent needs. It stops short of stating the default page size or what nextCursor looks like when the list is exhausted.

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 dense, front-loaded sentence that leads with the action and resource before the paging caveat. The trailing enumeration of returned fields is somewhat redundant given an output schema exists, but it is compact and does not obscure the primary instruction.

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?

With an output schema present, the return-value list is optional garnish, and the essential facts — ordering by reading order, optional part scoping, cursor-based paging — are all present for a three-parameter read tool. The only real omission is guidance on the undocumented limit parameter and terminal-page behavior.

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?

Two of three parameters are documented in the schema (part enumeration, cursor meaning), giving 67% coverage, and the description largely restates those same facts. The 'limit' parameter is undocumented in both schema and description, and no added guidance is given on sensible paging sizes or the 25 maximum.

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?

States a specific verb (List) plus a precise resource (the Capital Made Physical papers) with scope modifiers: 'in reading order, a page at a time, optionally for one of the seven parts (I to VII)'. This clearly separates it from get_paper (single record) and search_research (query-driven lookup) among the siblings.

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 conveys the browse/paging workflow by naming the part filter and the continuation cursor, which implies when to use it. But it never states when to prefer search_research or get_paper instead, nor any prerequisite for starting pagination without a cursor — the reader must infer that an absent cursor means page one.

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