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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, so safety is covered; the description adds genuinely non-obvious behavior — URLs are never returned because only a hash is stored, so a lost URL must be revoked and re-minted rather than recovered. That is exactly the kind of constraint an agent could otherwise hallucinate around.

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 sentences, front-loaded with what is returned, then the URL/hash caveat, then the scope exclusion. Each sentence carries distinct information with no restatement of the title or annotations.

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 not be spelled out (though they partly are). The remaining hole is how to build the required reference argument under 0% schema coverage; everything else an agent needs — scope, safety, and the recovery model — is present.

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% on a single required parameter, so the description must compensate. It does signal that the reference may be either a generation or an upload, which matches the anyOf discriminator, but it never says the value is an object with type/upload_id or generation_id, leaving the actual call shape to the schema 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?

States a specific verb and resource (list the live share links on one generation or upload) and enumerates the payload the agent will see: ids, ages, view counts, owner settings. It also draws a boundary that no sibling does — group links are not listable here — so the agent can distinguish it from create_share_link/revoke_share_link without opening a 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?

The scope phrase 'on one generation or upload' tells the agent the precondition, and 'A group's links are not listable here' is an explicit when-not. However, it never names where the agent should go instead for group links, so the routing is implied rather than complete.

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