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

Annotations already declare destructive, open-world, and non-idempotent behavior. The description adds useful context beyond them: list never returns a credential, provider_secret is kept sealed, the ChatGPT sign-in is revoked at OpenAI, the Claude box is deleted, and sign-in codes must be sent within 14 minutes.

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 content is mostly relevant, but it is delivered as a dense run-on paragraph with semicolon-separated action documentation rather than front-loaded structure. It would be much easier to scan as bullets per action, though most sentences still carry necessary procedural detail.

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?

Given five actions, OAuth flows, secret handling, and no output schema, the description covers the essential operational context: what list returns, how start and sign_in interlock, how keys are stored, and how remove behaves. Minor gaps remain around agent_key and the exact shape of successful responses, but an agent has enough to call the tool 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 coverage is only 29%, but the description compensates by explaining action-specific parameters: code differs by provider, provider accepts chatgpt/claude/openai_key/anthropic_key, provider_secret is the OpenAI/Anthropic key, and connection_id/model are used with set_model or remove. It does not explain agent_key or how to obtain connection_id, but overall it adds substantial meaning beyond the schema.

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 names the resource (model connections) and enumerates every action (list, start, sign_in, set_model, remove), so the agent can tell what the tool is for. The opening sentence is grammatically awkward and does not explicitly contrast with sibling tools, but the action list makes the scope unambiguous.

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?

It gives clear action-specific instructions: start with provider chatgpt/claude for plan-based sign-in, start with openai_key/anthropic_key for API keys, sign_in with the returned code, set_model with connection_id and model, and remove with connection_id. It does not explicitly name when to use this tool versus alternatives such as key_prepaid or model_eol, which keeps it from a 5.

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