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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuinely useful behavior: ordering (newest first), a 100-revision cap, the per-item payload shape, and a size warning that redirects to siblings. It omits however how to page past the cap, despite a result_offset parameter existing.

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?

Two dense, front-loaded sentences with zero filler: the first defines the operation and payload, the second handles the size caveat and alternate routes. Every clause earns its place.

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?

With no output schema, the description does the work of describing return values (fields, ordering, cap) which is the main gap it needed to fill. The remaining shortfall is paging behavior around result_offset, which matters for a tool that explicitly warns results can be large.

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 0%, so the description carries the full burden. It implies document scoping ('one document') and a 100-revision ceiling, but says nothing about project_id or how result_offset paginates past the cap — the one parameter whose meaning is genuinely non-obvious is left unexplained.

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 the published history of one document') and quantifies scope: up to 100 revisions, newest first, with the exact fields returned (revision, actor, created_at, full content). This is clearly separable from siblings like read_state and read_change, which the description names.

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?

Explicitly routes the agent away from this tool when output size is a concern, naming read_state for summaries of what changed and read_change for proposal diffs. It gives clear context for alternatives, though it never states the positive trigger (need full revision content) as crisply as the negative ones.

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