Read exact research text

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description still adds substantial behavior: paging with a byte budget that can return less than requested, hasMore scoped only to the selected target, ranges as UTF-16 code units with an exclusive end, an excerpt not being a complete document, and the stale_cursor recovery path. These are exactly the traits an agent needs to paginate correctly and to interpret hasMore without over-inferring completeness.

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 dense but front-loaded, opening with what is read and the small-page model before moving to cursor sourcing and edge cases. Each sentence carries operational content, though the stacked clauses about ranges, hasMore, and stale_cursor make the middle slightly hard to parse on first read.

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 two-parameter read-only pagination tool with no output schema, the description covers cursor provenance, paging limits, range units, the completeness caveat, and the error path, which is enough to call it correctly. It stops short of naming the fields a page object returns or how nextCall differs from cursor, so a little context is left implicit.

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 coverage is 100%, so the baseline would be 3, but the description adds real meaning: the cursor is only obtainable from another tool's read object and must be copied unchanged across calls, and page size is expressed in UTF-16 code units that truncate at UTF-16 boundaries rather than characters. It also clarifies that maxChars is a cap the byte budget may undercut, which the schema alone does not convey.

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 gives a concrete verb ('read') plus the specific resource types it returns (source text, notes, analysis, quotations, relationship notes) and states the paged delivery model. It does not explicitly distinguish itself from the sibling get_source_text or search_library, so the agent must infer that this tool is the cursor-driven continuation path rather than the initial retrieval.

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 tells the agent exactly where the cursor comes from (a readText/readMatch/readMore/nextCall object returned by another tool), when to advance (follow nextCall when more text is needed), and how to recover (repeat the original discovery call on stale_cursor). What is missing is an explicit statement of when to choose this over get_source_text or search_library, so the guidance is operational but not fully differentiating.

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