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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds two things annotations cannot express: the default unacked_only filter (a silent result-shaping default an agent must know about) and the required 'messages:read' scope, which is a real auth prerequisite.

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 short clauses, zero filler, with the behavioral default and the auth requirement front-loaded where an agent will see them before parsing the schema.

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?

There is no output schema, five parameters, and 20% schema description coverage, so the description should say more about what a page of results looks like and how to paginate (resume via after_seq = last seq received). It covers defaults and auth but stops short of that, which is a real gap for a polling tool.

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 only 20% — just after_seq is documented — so the description carries more burden than usual. It does explain the cursor semantics and the unacked_only default, but says nothing about limit (max 200), channel filtering, or workspace_id scoping, leaving three parameters undocumented in both places.

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 messages') plus the two defining behaviors: cursor-based and unacknowledged-by-default. That is enough to separate it from post_message and acknowledge_message, though it never names them explicitly.

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?

'after a cursor; unacknowledged only by default' implies the polling pattern and hints that unacked_only can be relaxed, but the description never says when to use this versus acknowledge_message or how to obtain an initial cursor. Usage is inferable rather than stated.

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