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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered; the description adds genuinely new behavior — reads do not advance or acknowledge read state, and optimistic concurrency via expected_revision means a changed feed must be re-read. Rate limits and page-size caps are left unstated.

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 read scope, then follow-up usage, then paging constraint. No filler or redundant restatement of the name.

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?

Output schema exists, so return values needn't be explained, and the acknowledging/paging semantics are covered. With eight parameters and near-zero schema descriptions, though, several filter parameters remain opaque, leaving the definition only partially complete for the tool's complexity.

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 only 13% (only source_path is annotated), so the description has to compensate. It clarifies the roles of offset and expected_revision, but leaves limit, unread_only, season_id, document_id and workspace_id entirely to the bare schema.

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 (read applied document changes plus this viewer's read state) and immediately differentiates itself from the acknowledgement path with 'without acknowledging anything', which separates it from mark_studio_document_changes_read and undo_studio_document_changes.

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?

Gives forward guidance on what to do with the result (use exact returned change IDs for mark-read or undo) and on paging via offset and expected_revision. It does not explicitly say when to prefer read_studio_document or which sibling covers unfiltered reads, so it falls just short of full alternative routing.

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