Bounded native pages

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

Annotations already carry the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower, and the description still adds real behavior: a stop-on-empty-page rule, a resume-page report when the 5-page cap is hit, and an explicit warning not to infer completeness from a short page. These are exactly the runtime traits that aren't visible in the schema and that prevent an agent from mistaking a truncated result for a full one.

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?

Three short sentences, front-loaded with the core action and the range, then the termination/resume rules. Nothing is padding, though the terseness leaves the parameters unexplained rather than being genuinely complete.

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?

This is a dispatcher over 12 operations with a fully opaque nested `arguments` object, 0% schema documentation, and no output schema. The description covers paging semantics well but omits the essential contract: what `arguments` should contain per operation, and what a page/resume report looks like. For a tool of this complexity, that is a substantial gap.

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, and it barely does. "1–5 pages" loosely restates max_pages, but the nested `arguments` object — the field that actually carries per-operation inputs — is never described, nor is how `operation` selects an underlying list call. An agent has no basis for populating `arguments` from the description alone.

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 verb and object are present ("Read 1–5 pages"), but the resource is described circularly as "a selected native paginated read," which is jargon an agent must decode. It never states plainly that this is a generic paging wrapper over the list_* operations, so distinguishing it from siblings like list_images or list_webhooks requires reading the operation enum in the schema.

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 explains stop conditions ("Stop at an empty page") and resumption ("report a resume page at the cap") but gives no guidance on when to use this batched pager versus calling the individual list_* tools directly. There is no condition, prerequisite, or alternative named, so routing between it and its dozen list_* siblings is left to inference.

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