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

Beyond the annotations (readOnly, idempotent, closed-world, non-destructive), the description discloses that access, subscription, and quotas are rechecked on every call and that a revision_changed signal invalidates the current read. Offsets are stated to be Unicode code points and page termination is defined via next_offset until null. Return payload shape is not described, but that is a minor gap.

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?

Front-loaded with the core action and prerequisite, and every sentence contributes operational information. The telegraphic sentence fragments ('Offsets are Unicode code points.') are efficient but slightly terse for a multi-step workflow.

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 a 6-parameter, read-only tool with no output schema, the description covers the pagination and revalidation loop well but leaves the meaning of scope, workspace, and current_source_hash unexplained in both schema and description. An agent would be guessing at those three arguments.

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. It meaningfully explains 'revision' (from preview_search) and 'offset' (Unicode code points, page until next_offset null), but says nothing about scope, workspace, or current_source_hash, leaving half the parameters undocumented anywhere.

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 one authorized memory page') plus the prerequisite input ('using a revision from preview_search'), which distinguishes it from the sibling preview_search. The closing sentence explicitly rules out reading arbitrary URLs, local files, or original documents.

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 an explicit workflow: obtain a revision from preview_search, then page through with offsets until next_offset is null, and re-run preview_search if revision_changed occurs. It also names the condition under which this tool is not the right one (arbitrary URL/file/document reads).

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