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

Annotations only declare readOnly=false, destructive=false, openWorld=false. The description adds substantial undisclosed behavior: the new key can never exceed the caller's capabilities, inherits the same source-IP limit, cannot have a later expiry or higher per-minute limit, is restricted to read scopes, and is capped at 20 keys per account per UTC day. That is exactly the kind of constraint an agent needs before invoking.

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 dense sentences, front-loaded with the action and its single-use return semantics, followed by the inheritance constraints and the permission prerequisite. No filler.

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 correctly discloses that the key is returned once. It covers the permission prerequisite and rate limit, but leaves roughly half the input parameters unexplained for a 7-param mutation tool.

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 description coverage is low (43%) across 7 parameters, so the description must compensate. It indirectly constrains ip_allow ('same source-IP limit') and expires_at ('no later expiry'), but says nothing about name, note, scope_mode, scope_rules, or account_scopes, leaving several parameters undocumented in both places.

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 ('Create a new API key on this account') and adds the crucial scope note that the key is returned once. Clearly distinguishable from siblings like everyinfra_key_update and everyinfra_key_delete.

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 strong context for when this is usable: it requires the keys:write account scope, which is off by default and grantable only by the owner. It does not explicitly name a sibling alternative, but the preconditions and the 'return it once' caveat effectively route the caller.

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