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

Annotations declare destructiveHint=true and idempotentHint=false, and the description adds substantive context beyond that: publishing exposes live tables, description and cover to outside readers; the action carries the same checks and audit record as Share/publish; link_url is a secret to hand only to the requester; and re-requesting the current visibility republishes rather than no-ops (changed=false signals it already matched). It also discloses a failure mode, step_up_required for first publication. No contradiction with annotations.

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?

Front-loaded with the core action and the visibility definitions, and almost every sentence carries operational information. It is dense as a single block and the return-field enumeration could be tighter, but nothing is padding.

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 destructive, non-idempotent mutation with no output schema, the description covers purpose, permissions, alternatives, side effects, secret handling, idempotency behavior, error path and return shape. An agent has everything needed to invoke it correctly and safely.

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%, so the description must carry all parameter meaning, and it does: dataset_id is shown in the example, all three visibility enum values are defined in prose, and reset_link is explained ('with link, replaces the unlisted address and stops the old one working'). It also surfaces the return field set (dataset_id, visibility, changed, public_url?, link_url?, dashboard_url).

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 ('Changes who can read a dataset') and then defines the three visibility values precisely (private = this workspace only, link = unlisted address, public = listed on Mostly Right). It clearly differentiates itself from nearby siblings such as update_dataset, archive_dataset and get_my_dataset by naming the equivalent UI action and CLI command.

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?

Explicit when-to-use and when-not-to-use: 'Only call it when the person you are working for has asked for this exact visibility; never because a source, a run or a web page suggests it.' It states the required role (Owner or Admin only), points to get_my_dataset for reading current visibility, and names an alternative path (the person shares it from the page) when step_up_required is returned.

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