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

Adds real behavior beyond the annotations: the link_taken failure mode, the fact that the original link keeps working after the change, and the plan requirement. Annotations already cover idempotency and non-destructiveness, so this is useful supplementary context rather than the whole burden.

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?

Dense and front-loaded: plan gate first, meaning and example next, edge cases (null removal, link preservation, error) last. Slightly telegraphic sentence fragments, 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?

For a three-parameter mutation with no output schema, it covers the prerequisite, the value format, the removal path, the failure mode, and the side effect on the old link. Only the return payload is unaddressed, which is acceptable without an output schema.

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 by fully specifying the slug grammar (lower-case letters, digits, hyphens; 3–40 characters) and the null sentinel for removal — none of which appears in the schema's bare string|null type. quest_id is self-evident by name and edit_token is documented in the schema.

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+resource ('give the quest a readable link') and immediately shows the concrete transformation with an example (slug "anna-30" → playUrl …/q/anna-30). This is unmistakably distinct from siblings like update_quest or share_quest.

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?

Provides a clear gate ('Quest+ only') and covers the removal case ('slug null removes it'), which tells the agent this same tool is used for both setting and clearing. It does not name an alternative tool such as update_quest for quests without Quest+, so the exclusion path is only implied.

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