get_unread

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

With no annotations, the description carries the full burden and handles it well. It discloses that messages are marked as read after retrieval, that behavior depends on whether a background service is running, and that the tool may poll signal-cli as a fallback. It also exposes the has_more continuation behavior, which is essential for correct invocation.

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?

The description is front-loaded with the core purpose and every clause contributes necessary behavioral or usage information. It is somewhat long and dense, but not wasteful. It earns a high score for efficiency while leaving a little room for tighter organization.

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 simple one-optional-parameter tool with no output schema, the description covers everything needed: how to invoke it, what happens after retrieval, and how to handle pagination. It even explains the background-service vs polling behavior, which is important operational context. No critical information is missing.

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 the limit parameter. The description adds meaning by explaining that 'limit' controls the batch size and that callers should reuse the same limit when continuing with has_more=true. This gives the parameter practical usage context beyond the schema's 'Max messages to return'.

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: 'Get new unread messages.' It also adds the directive 'Always use this to check for new messages,' which positions the tool as the primary entry point. However, it does not explicitly contrast itself with siblings like receive_direct or receive_messages, so it stops short of full sibling differentiation.

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 gives clear context for when to use the tool: it should always be used to check for new messages, and it explains the batching pattern with has_more. It does not explicitly state when not to use it or name alternative tools, so it lacks full when-not guidance.

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