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

Annotations mark this as non-read-only and destructive, and the description adds substantial context: company-manager-only permission, sensitive-tier approval behavior, key storage in Vault, the 'request≠grant' nuance, and the Is Agentic 404-until-scan caveat. This goes well beyond the annotations without contradicting them.

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?

The description is long but well-structured with line breaks and distinct sections (purpose, routing, sensitive-tier). Every sentence adds meaningful operational detail, though a few policy notes (e.g., 'do not re-ask in chat') could be trimmed for tighter focus.

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 tool with no output schema, the description is remarkably complete: it covers prerequisites, permission tiers, routing, post-connect behavior, and a known edge case (404 before scan). An agent has everything needed to decide when to call it and what to expect after the call.

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 all parameters. The description adds value with extra constraints: 'Never a private/loopback host' for server_url, 'At most 8' headers, and the default host behavior for name; it also clarifies that Authorization/API-key headers are refused and keys stay in Vault.

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 and resource: 'Bind a remote Streamable HTTP MCP onto this company from an https URL.' It also states the post-conditions (tools appear on list_integrations and run through invoke_integration), which distinguishes it from siblings like request_connector and start_oauth.

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 when-to-use and when-not-to-use guidance is provided: 'Use when an operator or GM wants this company to call a public Streamable HTTP MCP... without Composio or a host-seat paste' and 'Autonomous agents must call request_connector with a vetted name instead — they never supply a URL.' The routing section further clarifies Operator/GM vs. agent flow.

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