fetch_messages

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

With no annotations, the description carries the full behavioral burden, and it does disclose the critical side effect that reading marks messages read. However, it says nothing about whether it drains all messages or a page, error behavior, or what happens to already-read messages when unreadOnly is defaulted.

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 sentences, action first and trigger second, with zero filler. Every clause carries information an agent needs.

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?

An output schema exists so return values need not be explained, and the when-to-call guidance is complete. But for a five-parameter tool with no annotations and no parameter documentation, the definition leaves the agent guessing about scoping inputs.

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 description coverage is 0% across five parameters, so the description must compensate and instead adds no parameter meaning whatsoever — nothing about agentId/repo/repoId/projectId scoping or what unreadOnly=true (the default) means. Only the side-effect note tangentially hints that read messages are affected.

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 your inbox') and even flags the side effect in parentheses, so the agent knows exactly what the operation is. It stops short of explicitly distinguishing itself from other read-oriented siblings like pending or get_decisions, but the inbox framing is clear enough to route on.

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?

Gives a concrete, executable trigger: 'Call whenever claim_intent reports unreadMessages > 0.' It names the sibling tool that produces the condition and the exact field value that selects this tool, leaving nothing to inference.

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