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

Annotations only declare the safety profile (destructive, idempotent, non-read-only). The description adds substantial behavior the annotations cannot: replacement semantics when trigger_type changes, 409 mention_trigger_protected, 400 mention_trigger_workspace_required, 400 trigger_type_unsupported, and the fact that an existing @mention trigger's filter_config is left untouched rather than overwritten.

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?

Purpose is front-loaded in the first sentence, and the dense error-code/edge-case detail that follows is information-dense rather than filler. It is long, but every clause carries a distinct operative rule, so only mild trimming is possible.

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 5-parameter upsert with nested objects, no output schema and annotation-covered safety, the description covers prerequisites, replacement semantics, protected-resource behavior and three distinct error codes. It never says what the response contains (the resulting trigger object), which is the one remaining gap for an agent verifying success.

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?

With 100% schema coverage the baseline is 3, and the description earns an extra point: it explains that enabled:false pauses without deleting, that filter_config is replaced wholesale, and that teams_mention requires a filter_config.tenantId while Slack has no equivalent field. Some of this (whole-object replacement) is also in the schema, so it is not entirely additive.

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 first sentence gives a precise verb pair (create or update) and resource (the authenticated user's trigger for an integration on an agent), and the upsert scope is immediately evident. An agent can tell this apart from the specialized createAgentSlackTrigger/createAgentCaseTrigger variants and from deleteAgentTrigger without opening any schema.

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 states a real prerequisite (the integration must already be connected via OAuth in the dashboard) and a routing recommendation (@mention triggers should be managed from the agent's mention setting throughout). It stops short of naming the alternative tools (e.g. listAgentTriggerTypes to discover valid values) explicitly, so the agent must infer the siblings.

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