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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds genuinely non-derivable behavior: the deletion propagates to every user the skill is shared with, and previously produced answers remain in their chats. What's missing is failure behavior (does a non-author call error or no-op) and whether deletion is soft or permanent.

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 short sentences with the blast radius front-loaded and no filler. The final sentence is elliptical ('Only its author or an owner of its team may.') and reads slightly clipped, costing a bit of precision.

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?

An output schema exists, so return values need no explanation. For a destructive single-parameter delete, the description covers blast radius, data retention side effects, and authorization — everything an agent needs before calling.

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 0% for the single skillId parameter, so the description carries the burden, yet it never mentions the identifier at all. The parameter name and uuid format make the intent inferable, so this is adequate rather than broken.

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 ('Delete a saved skill') and immediately scopes the effect ('for everyone it is shared with'), which cleanly separates it from skill_update, skill_list, and the unrelated *_delete siblings like question_delete and display_logic_rule_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?

Conveys a prerequisite ('Only its author or an owner of its team may') that tells the agent who can invoke it, but gives no when-to-use framing versus alternatives such as skill_update (to change it) or unsharing, and no when-not-to-use condition.

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