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

With no annotations at all, the description carries the full burden and does explicitly declare "Read-only" plus the no-connection return value, which are the two facts an agent most needs. Remaining gaps (auth/permission requirements, error behavior for unconnected providers, rate limits) are minor for a single-resource read.

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?

Three short clauses: what it returns, when to call it, and its safety profile. The return shape is front-loaded and nothing is redundant.

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?

No output schema exists, so the description must hint at the response, and it does so with "status and settings" and the {connected:false} case. For a one-parameter read tool this is largely sufficient, though richer return shape detail would remove the last inference.

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 0% but there is only one parameter with an enum, and the description maps the enum values to human labels (Kommo, HubSpot). That is enough to make the single required argument unambiguous without repeating schema mechanics.

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 resource (the Kommo or HubSpot connection) and what is returned (status and settings), plus the empty-state shape {connected:false}. It is distinguishable from connect_crm_integration and roughly from list_crm_integrations, though it never names the list tool as the multi-connection alternative.

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?

"Use it to poll after connect_crm_integration" gives a concrete triggering context for invocation. It stops short of exclusions (e.g., use list_crm_integrations to enumerate all connections, get_crm_integration_logs for diagnostics), so sibling routing is only partially resolved.

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