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

Annotations already declare a safe, idempotent read, and the description adds behavior annotations cannot carry: the exact response row shape, the fact that connection_label is a JSON string that must be parsed before display, and the interaction rule to ask the user when multiple accounts exist.

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?

Dense and front-loaded: purpose, then return shape, then how to use the result, then the fallback. The opening sentence is slightly garbled in phrasing, but every sentence earns its place and nothing is padded.

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?

With no output schema, the description carries the full burden of explaining return values, and it does so field by field, including the JSON-string gotcha in connection_label. It also closes the loop on the natural next step (create_connection_link) so the agent is not left guessing.

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?

There are zero parameters, so the baseline is 4. Saying 'Body {}' confirms no input is required, which is mild but useful confirmation rather than new parameter semantics.

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+resource: it lists the app accounts the signed-in user has connected. It also enumerates the returned fields (auth_id, service_id, service_name, connection_label), so the agent knows exactly what this returns without opening any 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: match service_id to find the auth_id an action or automation needs, ask the user which account when there are several of one app, and fall back to create_connection_link when the app is absent. That names the alternative sibling and the condition that selects it.

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