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

The description adds genuine context beyond the annotations: grant/room scoping is an authorization constraint, and 'fetching does not attest reading' flags a semantic distinction between delivery and acknowledgement. However, it never reconciles readOnlyHint=false with a tool literally named read_tool_page - it does not say what state fetching changes (presumably cursor advancement), which is the key behavioral fact an agent needs.

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 sentences, front-loaded with the return shape (json_fragment, next_cursor) and zero filler. The second sentence is compressed to the point of opacity ('batch eligibility') but is not padded.

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 only two parameters, annotations present, and no output schema, naming the returned fields is the right compensation and it does so. Remaining gaps - cursor expiry and the non-read-only state change - are the only things keeping it from fully complete.

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 50%: room_id is documented in the schema, cursor carries only constraints and no description. The description partially compensates by characterizing cursor as 'a result cursor' (opaque, from a prior call) and implying room scoping, but it says nothing about cursor origin, lifetime, or validity.

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 states a specific verb and resource ('Returns the next ... frozen JSON fragment for a result cursor'), so an agent can tell this is a cursor-based page fetcher. But the phrasing 'grant- and room-scoped frozen JSON fragment' is jargon-dense, and among ~60 siblings it never names the closest alternatives (read_around, read_attachment, read_message) or states how it differs from them.

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?

Usage is only implied: the word 'next' plus 'for a result cursor' signals continuation of a paginated result, but there is no explicit 'call this after X returns a cursor' or 'do not use for initial reads'. No alternatives or exclusions are named.

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