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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=true, so safety and repeat-call behavior are covered. The description adds context the annotations do not: the operation is limited to TikTok, the effect is visibility ordering on the post, and it should only fire on explicit user intent. It does not say what happens when the post or comment is not TikTok-eligible (error vs. no-op).

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?

Two short clauses with the action, its scope and its inverse front-loaded, then the usage constraint. No filler, no restatement of the title, and every sentence carries information an agent would otherwise have to guess.

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 two-parameter toggle with no output schema, the description supplies what matters: platform restriction, inverse semantics, provenance of the identifier, and the intent requirement. Remaining gaps are error behavior on non-TikTok posts and whether unpinning has any restriction, which are minor but real for an openWorldHint write tool.

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?

With only 50% schema coverage — the 'pinned' parameter has no schema description — the description carries the key meaning by explaining that pinned=false performs the inverse operation, which is not derivable from a boolean default of true alone. It also ties comment_ref back to list_comments, reinforcing the schema's own hint. Minor gap: no format or example for comment_ref beyond its source tool.

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 ('Fija un comentario ... arriba de su publicación') plus a platform scope ('solo TikTok') and the toggle direction (pinned=false lo desfija). It also names the sibling that supplies the input ('de list_comments'), so an agent can separate it from hide_comment, like_comment and resolve_comment 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?

Gives an explicit use condition — 'Úsala solo cuando el usuario lo pidió' — which is a real gating rule, especially valuable because pinning is a public-facing visibility change. It does not name the adjacent moderation alternatives (hide_comment, like_comment, resolve_comment) or say what to do instead when the target post is not on TikTok, so exclusions are only partial.

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