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

Annotations only declare that this is a non-read-only, non-destructive write, so the description carries the real burden and does: scopes default to the caller's and may never be wider, a 5-key trial ceiling, trial-scope clamping while the owner is unverified, one-time secret return ("store it"), and team-key revocation on leaving the team. These are non-obvious consequences an agent must know 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?

Front-loaded with the action, then constraints, then the one-time-secret warning — every sentence carries information. The semicolon-chained space/team clause reads slightly run-on and could be split, but nothing is wasted.

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 an output schema exists, return shape needn't be explained, yet the description still flags the one-time secret return, which is critical. Trial limits, scope inheritance, and team semantics cover the tool's complexity; only the label parameter goes unaddressed.

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 33%, and the description compensates for the two undocumented parameters: it explains the scopes default and the never-wider constraint, and elaborates the "team" value of space beyond the schema's own text. label remains undescribed, though its meaning is self-evident.

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?

"Makes a new key on your own account" states a specific verb and resource with scope (own account), and the narrowing example clarifies the typical intent. It is clearly distinguishable from siblings such as list_keys, revoke_key, and create_nod 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?

Gives an explicit use case ("a narrower one for a helper") and conditions: trial accounts capped at 5 live keys, unverified owners cut to trial scopes, and team keys only where teams exist. It stops short of naming alternatives like revoke_key or use_key, but the when-to-use context is clear.

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