pending

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

With no annotations, the description carries the full burden and does disclose the key behavioral trait: 'Read-only ... Marks nothing read,' making the side-effect-free nature explicit. It does not cover auth requirements, scoping, or rate limits, but the most important behavioral fact (it is a non-mutating nudge) is front and center.

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 tight sentences, front-loading the read-only count semantics and then the follow-up routing. Every clause earns its place with no 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?

An output schema exists, so return values need not be explained, and the '> 0' condition hints at the count. However, the four undocumented filter parameters leave a real gap for an agent deciding how to scope the call, so it is only minimally complete.

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?

Four parameters (agentId required, plus repo, repoId, projectId) have 0% schema description coverage, and the description explains none of them. Whether the count is scoped by repo/project is left entirely to inference, so the description fails to compensate for the coverage gap.

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: a read-only count of unread messages and open tasks. It implicitly distinguishes itself from the listing siblings (fetch_messages/list_tasks) by framing itself as a count/nudge rather than a full read. It does not explicitly name itself against those siblings, but the purpose is unmistakable.

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 gives a clear conditional trigger: 'if it returns > 0, call fetch_messages / list_tasks,' routing the agent to the correct follow-up tools. It stops short of stating when not to use it (e.g., when you already know you need full content, skip the count), so it is clear context without explicit exclusions.

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