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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavior: output capped at 20k characters with explicit pagination, snapshot mandatory because stale refs are rejected, and groupId being included by default (null = ungrouped). It stops short of describing error or empty-result behavior.

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 purpose is front-loaded in the first clause, and each following sentence covers one distinct topic (fields, query, bounds, snapshot) with no filler. The telegraphic, colon-and-parenthesis style is dense but efficient; a slightly clearer separation of the refs vs query modes would improve scanning.

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 an 8-parameter, no-output-schema read tool with zero schema coverage, the description supplies mode semantics, property projection, query syntax, result bounding and the snapshot contract. Missing pieces are the source parameter (draft vs published) and any hint about result shape beyond the character cap, which the absent output schema leaves undocumented.

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 carries the full burden and largely does: it explains refs, query (empty = no filter, | = literal OR, not regex), fields (dot-path property selection with concrete examples plus id/sectionId/sectionRef for composition), snapshot, and limit/offset pagination. Two parameters remain unexplained: source (draft|published enum) and pageId, which is a real gap at 8 parameters.

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 opens with a precise verb+resource: reading targeted section definitions for several refs in one call, or searching by query. It clearly conveys the two operating modes (refs vs query) and the property-selection purpose of fields. It does not name the sibling it supersedes or complements (get_page_blocks, get_page_structure, get_page_outline), so sibling differentiation is left to inference.

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 implies when each mode applies: refs for known sections, fields for partial reads during composition, query for searching by labels. It also states the snapshot prerequisite. However, it never says when to prefer this over get_page, get_page_blocks, get_page_structure or inspect_page_region, so the agent must guess among near-duplicate siblings.

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