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

Beyond the readOnly/idempotent/not-destructive annotations, it discloses the required scope (anonping:read), the absence of automatic read receipts, the text-only nature of responses, and the key edge case that media and removed messages carry null content yet still advance the cursor. It also flags conversation text and contact labels as untrusted data subject to prompt injection, which is genuinely useful safety context.

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-loads the core operation and keeps every sentence purposeful: polling contract, behavioral caveats, then the safety and scope notes. Slightly dense with three-plus distinct concerns stacked together, but no sentence is filler.

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 steps in to describe the key return fields (nextCursor, hasMore, retryAfterMs) and the null-content edge case. Scope, safety, and cursor semantics are all covered, so an agent has what it needs to call this correctly.

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 all three parameters are already documented in the schema. The description references the cursor concept but adds no format, range, or default detail beyond what the schema provides, making the baseline 3 appropriate.

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+resource ('Read retained messages') plus a retrieval model ('after a sequence cursor'), and rules out a competing model with 'No push/background subscription.' It doesn't name or differentiate against siblings like list_conversations or get_status, so it falls short of a 5.

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?

It implies usage through the polling contract ('Immediate polling: use nextCursor, hasMore and retryAfterMs') and the absence of push, telling the agent to poll rather than subscribe. But it gives no explicit when-to-use-it-over-alternatives guidance relative to siblings such as list_conversations.

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