create_api_key

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

Annotations already establish write/non-read-only, non-destructive, non-idempotent, closed-world, so the description is not obligated to restate them. It adds genuinely non-derivable behavior: the call mints a secret requiring confirmation, scopes are capped by the calling key's scopes, and team-management/portal permissions are deliberately never inherited and must be enabled in /dashboard/api. The one omission is what the response returns (i.e., that the secret itself is surfaced once).

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?

Front-loads purpose then the safety gate in caps, followed by tight constraint sentences. No filler, and the ordering mirrors the agent's decision path (what it does, whether to call it, what it will and won't grant).

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?

Five fully documented parameters and no output schema mean the definition need only cover intent, safety gating, and scope constraints, all of which are present. Nothing an agent needs to decide whether and how to invoke it 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?

Schema coverage is 100%, so the baseline would be 3, but the description adds real meaning beyond the schema: the inheritance rule for 'scopes' relative to the calling dashboard key and the explicit carve-out that members:read/members:write and client-portal sign-in-link permissions are never copied or granted through this tool. Those are semantic constraints an agent could not infer from the field descriptions alone.

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?

Names a specific verb and resource ('Create a new posterly API key') plus the actor scope ('for the authenticated user'), which cleanly separates it from sibling delete_api_key and the dashboard/workspace tools.

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?

Explicitly gates usage ('only use after explicit user confirmation') and names when it cannot be used ('OAuth and managed assistant tokens cannot mint keys'), which covers the critical alternatives. It stops short of naming a sibling alternative for the excluded permission cases, instead pointing to the dashboard UI.

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