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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so the safety profile is covered. The description adds behavior the annotations cannot convey: the implicit default filter of new/un-reviewed, a hard cap of the newest 20 results, and the absence of paging. It does not say what a returned signal contains, though the absence of an output schema makes that a modest gap.

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?

Three sentences, front-loaded with what the tool lists, then the filter default, then the result-size constraint. Every clause carries information an agent needs, and the most surprising constraint (no paging, 20 newest) is placed last where it lands as a caveat.

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 three-parameter read-only list tool with full schema coverage and annotations, this covers what an agent needs: what is listed, what the default filter is, how to widen it, and how many results come back. No output schema exists, so the description's cap and no-paging note are the right level of return-value context.

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 baseline is 3. The description earns above baseline by glossing 'new' as un-reviewed and clarifying that status selects the saved/reviewed/dismissed/all subsets, which is more than the terse enum labels in the schema. It adds no clarification for the required context or projectId parameters, but those are self-documented.

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?

Specific verb plus resource plus scope: lists user signals for a project and enumerates the kinds (feedback, bug reports, feature requests, observations) and their origin (users or manual). That enumeration distinguishes it from siblings like signals_get (single item) and signals_capture (creation) without those tools being named.

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 concrete selection guidance: it defaults to new/un-reviewed signals, and the caller passes status for saved, reviewed, dismissed or all. That covers the main when-to-use decision for this tool. It stops short of explicitly steering to sibling tools such as signals_get for a single signal or feedback_hub_get for aggregate feedback.

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