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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered structurally. The description adds the provenance requirement for event_id but says nothing about pagination behavior, result shape, or how 'get' differs from 'list' beyond the action field, leaving behavioral gaps that annotations don't fill.

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?

Two compact sentences, front-loaded with the resource and scope, with the constraint placed last. No filler, though the middle 'Dispatch via action' sentence is terse enough to be slightly cryptic about the available modes.

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?

The tool has an output schema and full annotations, so return values and safety needn't be described. The description covers purpose, dispatch, and the key input dependency; only minor gaps remain around what each action returns and pagination, which the schema mostly handles.

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 schema already documents event_id provenance ('Event UUID returned by search_events'), page semantics, and the action enums. The description's note that event_id must come from search_events largely repeats the schema, so it adds minimal value beyond the documented baseline.

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 ('Read services for the provided event') and implies a dual mode via 'Dispatch via action'. It is clearly distinguishable from create_service/update_service/delete_service siblings by the read verb, though it doesn't spell out what the 'list' vs 'get' actions actually return.

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?

Provides one concrete prerequisite: event_id must be the UUID from search_events, which usefully chains calls. However, it gives no guidance on when to prefer this over read_event_content or other read siblings, and 'Dispatch via action' only hints at mode selection rather than stating the condition for list vs get.

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