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

Annotations already declare a safe read (readOnlyHint true, destructiveHint false), so the bar is lower. The description nonetheless adds real behavioral value: total is present only on the first page, pages end with next_cursor, and cursor reuse requires identical arguments — all non-obvious traits.

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?

Front-loaded with the resource and its scope, then pagination semantics. The filter list largely restates enum values already in the schema, which is mild duplication, but the text is dense and there is no filler.

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 10-parameter, paginated read tool with full schema coverage and an output schema, the description covers scope, filtering, pagination and notebook selection. Return-value shape is handled by the output schema, so nothing essential for a correct call 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?

Schema coverage is 100%, so baseline is 3. The description goes beyond the schema by explaining the cursor round-trip contract and the special 'all' value for notebook_id along with the omit-for-default behavior, which helps the agent chain calls correctly.

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 and resource ('The user's words, a page at a time') and enumerates the available filter dimensions, so the agent knows exactly what the tool returns. It does not differentiate itself from close siblings like search_words or get_due_words, which overlap heavily with the filter set described here.

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?

Pagination usage is spelled out well — pass next_cursor back as cursor with the same arguments. But there is no guidance on when to pick this over search_words, get_due_words, or get_recent_words, which the agent must infer from overlapping functionality.

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