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

Annotations already declare readOnlyHint, idempotentHint and closed-world, so the bar is lower. The description still adds real substance: newest-first ordering, grouping by run, pending-only default, the shape of each item ('changes' holds proposed values), and the notable cost fact that it uses no AI and no credits.

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 dense sentences with no filler; scope, grouping, ordering, item shape and cost are all front-loaded. Nothing could be cut without losing 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 detailed, and the description still covers the salient ones. Params, ordering, grouping, defaults and cost are all present; only result-size or paging behaviour is unaddressed, which is a minor gap for a filtered list.

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 67% and the undocumented `operation` parameter is compensated for: the description names the four run types (Analyze, Generate, Audit backlog, Propagate stories) that map to its enum values. It also documents the default for `status` ('Pending only by default'), adding meaning beyond the schema.

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+resource ('List AI suggestions') with scope and grouping semantics ('grouped by the run that made them'), and enumerates the four run types by name. It is clearly distinguishable from the sibling write tools suggestions_accept and suggestions_reject.

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?

Usage is implied by 'waiting for review' and the default 'Pending only', which sets up the review workflow that siblings suggestions_accept/reject complete. However, it never explicitly says when to choose this over alternatives or when to widen the status filter, nor does it mention prerequisites for the review flow.

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