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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the description's job is to add value beyond that. It adds 'including review and resolution data' — clarifying the return content — which is genuinely useful behavioral info about what the response covers. No contradiction with the annotations, and the description supplements rather than duplicates them.

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?

One well-formed sentence that front-loads the trigger condition ('Use this when...'), specifies the task, and clarifies response scope. Zero filler words, no repetition of schema data, maximum information density.

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 100% parameter schema coverage, full annotations (readOnlyHint, idempotentHint, destructiveHint, openWorldHint), and an output schema present, the description's job is minimal. It correctly adds the 'including review and resolution data' detail that the schema doesn't convey. It could mention edge cases (e.g., invalid/nonexistent ID), but with the output schema and robust annotations, coverage is sufficient.

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% — the single 'signalId' parameter is fully documented in the schema with type and description. The description adds the 'full details... by ID' context and mentions 'review and resolution data' in the return, which loosely reinforces that signalId refers to a signal. Per the rubric, with coverage at 100%, the baseline is 3, and the description doesn't add parameter semantics beyond schema (which is 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 clearly states the verb ('Use this when the user needs'), the resource ('full details for one AI signal'), and the scope ('by ID, including review and resolution data'). 'One... by ID' explicitly distinguishes this from the plural get_signals sibling, and it precisely names the return-content focus via 'review and resolution data.'

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 begins with 'Use this when the user needs...', which is an explicit usage-trigger instruction. The singular 'one AI signal by ID' implicitly contrasts with list-style siblings like get_signalsversus get_signal_stats, though it does not name the alternative directly. A named alternative would have made this a 5, but the 'Use this when' framing provides a clear decision rule.

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