Check signals

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

The description discloses a real side effect – 'Automatically marks them as read' – which is exactly the kind of behavioral context annotations cannot express, and it explains why (to avoid re-narration). However, that side effect conflicts with the declared readOnlyHint=true, since read-state is modified by the call. The disclosure is useful but it contradicts the structured safety signal, leaving the agent unsure which to trust.

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?

Four short sentences, each doing distinct work: when to call, what it returns, what to do with the output, and the side effect. Front-loaded with the trigger condition.

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 covers return content (unread signals by source), the expected agent action (narrate), and the mutation (mark as read). It omits edge cases such as what happens when nothing is unread or how signals are ordered, which keeps it just below 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?

There is one optional parameter with 100% schema coverage, including an inline example ('chatgpt-codex-worker2') and its purpose ('read attribution'). The description adds nothing about agent_id, but the schema does that job completely, so the baseline of 4 applies.

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 ('check signals', 'returns unread signals') and enumerates the sources (TestPass, Crews, Memory, UnClick tools), so it is distinguishable from siblings like check_inbox or read_messages. The session-start framing ('catch up on what happened since the user last chatted') makes the resource scope concrete.

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?

Explicit timing instruction: 'Call at the start of every session.' It also specifies the follow-up obligation ('narrate the important ones to the user'). It does not name when NOT to call or contrast with inbox-style siblings, so it stops short of a 5.

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