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

Annotations only declare a non-read-only, non-destructive, non-idempotent mutation; the description adds substantially more. It discloses the lifecycle (the share lasts until expiry or revocation), what recipients can see (text lines, status, source), and the Unverified labeling path when the playlist or school policy has not been reviewed. That edge-case disclosure is the kind of behavior an agent cannot infer from annotations or schema.

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?

It is front-loaded with the core action, then the usage rule, then inputs, then returns and the unverified caveat. The restatement that expires_at is required and must be in the future duplicates the schema, but overall there is little waste.

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 explains the return values (share_id and the share link) and how the link behaves over time. The main remaining gap is the shape of the nested snapshot object, which is only described as "stored exactly as given" in the 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 description coverage is 100%, so all four parameters are already documented, and the description largely restates them (run_token, snapshot, includes_grades, expires_at in the future). It adds only mild framing such as "the snapshot the person chose to share" and does not clarify what fields the nested snapshot object should contain.

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?

The description opens with a specific verb and scope: "Share one run." That separates it from playlist_unshare and from read-oriented siblings like playlist_read or playlist_open without needing the schema. It also states the result (share_id plus a link), so the agent knows exactly what the call produces.

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?

"Call this only when the person asks to share" is an explicit activation condition and an implicit exclusion for speculative or proactive sharing. It does not name the inverse tool (playlist_unshare) or describe preconditions such as needing a run_token from a prior answer, so the guidance is clear but not exhaustive.

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