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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description does add one piece of non-structured context — that the refs are temporary — which hints they expire, but it never says how long they live or whether a new call invalidates prior refs.

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?

A single front-loaded sentence with no filler, though the trailing subordinate clause attaches the usage condition rather than the core action, which slightly buries the verb+resource.

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?

An output schema exists so return values need not be explained, and annotations carry safety. What is missing is routing: in a 32-sibling document toolset, the agent still cannot tell from this description when outline beats find, get_context, or read_context.

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 all six parameters are documented in structured form, including the operation_id retry/replay semantics and the private document token. The description only obliquely touches `within` via "temporary read refs"; baseline 3 for full schema coverage is correct.

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?

Names a specific verb (lists) and specific resources (headings or code declarations) plus the artifact it produces (temporary read refs). It is distinguishable from document.find or document.read_context, but the phrase "when choosing which part of a document to inspect" muddles the what with the when rather than sharpening the differentiation.

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 clause "when choosing which part of a document to inspect" implies the usage context (orientation before deeper reads), but it never names an alternative or an exclusion. With siblings like document.find, document.get_context, and document.read_context present, the agent has to infer which orientation tool applies.

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