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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered by structured data. The description adds real context beyond that: the access-tier gate that rejects non-read operations and the credential-resolution rule when multiple connections exist. It stops short of noting rate limits, provider-specific failure modes, or error behavior, which matters for an open-world tool.

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 tight sentences, zero filler, with the core purpose front-loaded before the access restriction and the credential caveat. Every clause carries decision-relevant information.

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?

That an output schema exists relieves the description of explaining return values, and the routing/authorization rules are well covered. However, for a generic passthrough with five parameters including a free-form nested object, the absence of any guidance on how to construct `resource`, `operation`, and `params` leaves a meaningful gap an agent must resolve elsewhere.

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 40% schema coverage, the description must compensate, and it largely does not: `resource` and `operation` are undocumented in both schema and description, and `params` (a free-form nested object) has no explanation of what keys it accepts or how they map to the operation. Only `credentialId` semantics is addressed, and it largely restates the schema's own description.

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 gives a specific verb and resource ('Run a READ integration operation') and anchors it with concrete examples ('list Slack channels or fetch channel history'), so an agent knows this is a generic passthrough for read-scoped provider calls. It does not spell out the relationship to integration.list_operations/list_options beyond referencing them as the source of truth, which keeps it short of a full 5.

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 ('only operations integration.list_operations reports with access `read`') and when-not ('use integration.execute for `write` and `destructive` ones'), naming the alternative and the selection condition. It also states the credential precondition (optional when the provider has exactly one connection), leaving nothing to inference.

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