integrations_read

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

The annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description goes beyond that by disclosing troubleshooting content (agent_integrations surfaces missing calendars, deleted connections, quiet inboxes), the caching behavior around zoho_fields/force, and the compact-vs-full response payload tradeoff. It stops short of stating rate limits or return shapes, which keeps it at 4 rather than 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?

It is front-loaded correctly, opening with purpose and routing, but the body is a dense wall of text that repeats itself: the 'resources' drill-down is described once in prose and again in the actions list, and the integration enumeration appears twice. Every sentence is defensible in isolation, yet the redundancy costs scan-ability for an agent parsing eleven actions.

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 an 11-action, 14-parameter dispatcher with no output schema, the definition covers what each action needs and roughly what it returns, including the debugging use case. The main remaining gap is the shape of returned connection/resource objects, but the action-by-action 'Needs:' mapping plus the mode flag gives an agent enough to call it correctly.

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 86%, so the per-parameter docs already carry most of the load. The description still adds real semantic value by binding parameters to actions ('Needs: agentId', 'Needs: connectionId, moduleApiName') and by explaining the baseId → tables → fields and sheetId → tabs → headers drill-down paths, which the flat schema cannot express.

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 states a specific verb and resource ('See every integration of the workspace exactly like the dashboard Integrations page') and enumerates the eleven integrations covered, so scope is unambiguous. It also draws a hard line against the write/test siblings by noting that writes go through integrations_write and integrations_test, letting an agent separate this tool from its nearest neighbors without opening the 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?

Explicit routing is given: 'Start with all_connections ... then agent_integrations to see and debug what one agent has configured', followed by when to use resources and each of the narrower actions. It also states a precondition — the first OAuth connection is always made by the user on the dashboard — which prevents an agent from trying to create a connection here. That is an unusually complete when/when-not/alternative statement.

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