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

Annotations already declare destructiveHint=true, idempotentHint=false, and readOnlyHint=false, so the safety profile is structured. The description goes further by disclosing the two facts an agent most needs and cannot infer: the new key is shown only once, and the old key stops working immediately. Missing only auth-level prerequisites, which is minor given the annotation coverage.

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 sentences, front-loaded with the action, and the second sentence is dense but every clause is actionable (save the key, update the header first). Slightly long in the second sentence but no filler or repetition.

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 zero-parameter, irreversible mutation with no output schema, the description covers what changes, what is lost, what must be saved, and the required follow-up action. Nothing an agent needs in order to call it safely is missing.

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?

The tool takes zero parameters, so there is no parameter semantics to explain; the baseline for a 0-param tool applies. The description correctly implies no input is required beyond the existing authenticated connection.

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 and resource ('Replace the API key this connection uses') plus the exact outcome: a new key is issued and the current one revoked in one step. It scopes the audience ('AI-agent accounts from register_agent'), which separates it from the read-oriented siblings like get_run_log or list_my_signals.

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?

Gives clear operational context: this applies to agent accounts created via register_agent, and the caller must save the new key and update the Authorization header in their MCP client before any other call. It stops short of naming when-not-to-use (e.g., human/PAT accounts), but the eligibility scope is explicit enough to act on.

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