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

Annotations already declare readOnly=false, idempotent=true, destructive=false, so the safety profile is covered. The description adds a real behavioral fact — the auth scope and that the CRM is not contacted directly from MCP — but says nothing about whether the sync is async, what job/handle it returns, or how long it takes.

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?

Short and front-loaded, but the 'APP:' tag adds nothing and the closing negatives ('does not call the CRM from MCP and does not publish a web page') spend a full sentence on disambiguation that is not obviously relevant to a caller.

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 no explanation. However, for a non-read-only, seven-parameter sync trigger with no required fields documented anywhere, the description omits what is minimally required to invoke it correctly and what the call actually kicks off.

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?

Seven parameters with 0% schema description coverage and zero parameter guidance in the description. The names (id vs. integrationId, externalProjectId/externalCampaignId/externalObjectiveId/externalCorrelationId, idempotencyKey) are genuinely ambiguous and the description clarifies none of them, so the agent must guess which identifiers are needed.

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 ('Requests a CRM integration sync') and names the API surface, which separates it from read-only siblings like get_integration_status or list_integrations. The 'APP:' prefix is noise but the core action is unambiguous.

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 a prerequisite ('Requires integration:write') and two negative boundaries ('does not call the CRM from MCP', 'does not publish a web page'), which implies this only enqueues a sync. It never explicitly says when to pick this over get_integration_status (check vs. trigger), leaving the main routing decision to inference.

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