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

No annotations are provided, so the description carries the full burden. It discloses that pagination is cursor-based (next_cursor) and that results exclude own sends, which is helpful. But it doesn't state whether this is a read-only operation, pagination stability, or rate limits.

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?

A single dense sentence front-loads the scope, ordering, and pagination instruction with zero waste. 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?

For a read/list tool with complete parameter schema but no annotations, the description covers scope and pagination. It omits whether the operation requires auth (tenant_key implies it), whether it's read-only, and what the return shape looks like.

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 100%, so the schema already documents all four parameters thoroughly. The description adds pagination semantics (use next_cursor from previous response), going beyond the schema's terse 'Opaque; omit for first page.'

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+resource: retrieves messages across all threads the agent participates in, excluding own sends, ordered oldest first. The scope and ordering distinguish it from siblings like host.msg.thread (single thread) and host.msg.ack (mutating).

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?

The description implies when the result is filtered (all threads, not own sends) but doesn't explicitly state when to use this versus host.msg.thread. Usage is inferrable from the scope but no alternates are named.

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