incident_incident_comments__list_incident_comments

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds two genuine behavioral facts beyond that: results are filtered to what the caller can access (permission-scoped visibility) and comments come back ordered by create_time. Pagination behavior is not discussed, which keeps it from a 5.

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?

Front-loaded with the action and endpoint, then the scoping rule, then ordering — a sensible priority order. The middle sentence ("The user must always specify the uuid... therefore, the list is always provided only for one Incident") is slightly redundant, restating the same constraint twice.

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 simple two-parameter read-only list endpoint with no output schema, the definition covers the required parent identifier, visibility scoping, and result ordering. What an agent might still want — the shape of a comment object and whether result sets can be large enough to page — is not addressed, but the rich annotations and full schema coverage compensate.

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 description coverage is 100% — incidentUuid's format/length/required semantics and the 'fields' server-side projection are already fully documented in the schema. The description restates that incidentUuid must always be supplied but adds no new syntax, defaults, or semantics. Baseline 3 applies when the schema does the heavy lifting.

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 opens with a specific verb+resource ("List incident comments") and reinforces it with the backing endpoint (GET /v2/incidents/{incidentUuid}/comments) and the exact scope (comments accessible to the caller, always for one incident). An agent can immediately tell this apart from the sibling get_incident_comment (single-record fetch) and from incident_incidents__list_incidents.

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 clear invocation context: incidentUuid is mandatory and the result set is always narrowed to a single incident, so the agent knows a parent Incident must be resolved first. It stops short of naming alternatives (e.g. when to use this vs. get_incident_comment or incident_full_context) or stating exclusions, so it does not reach a 5.

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