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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description goes further by disclosing the full-replacement semantics, that grants omitted from the payload are actively revoked, and that the change is irreversible. The only tension is that a replace-all set operation is normally idempotent, while idempotentHint=false is declared; the description neither explains nor contradicts this, so no hard contradiction is asserted.

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 clauses, roughly a dozen words, with the destructive action and its revocation scope front-loaded. Nothing is padded and nothing needs rereading.

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, no-output-schema mutation, the description covers the essential risks: full replacement, revocation of omitted grants, irreversibility, and approval gating. It leaves open an edge case the schema implies but does not resolve — whether grants are ignored or rejected when visibility is 'private' or 'org' — which keeps it short of a 5.

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 100% and the visibility enum and grants array are already documented in the schema, so the baseline is 3. The description adds genuine meaning beyond that by explaining the consequence of the grants payload — anything not listed is dropped — which is the single most important semantic for populating the array correctly.

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 uses a concrete verb plus resource ('Replace all sharing' on the dashboard named in the title), and the phrase 'omitted grants are revoked' pins down that this is a wholesale set rather than an incremental add. It does not explicitly name a sibling (e.g. report_get_sharing for reading, report_add_block for unrelated writes), so the differentiation comes mostly from the title.

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 phrasing 'after explicit approval' implies a confirmation-gated workflow and tells the agent this is not a casual call, which is real guidance. However, it never states when to prefer this over report_get_sharing / report_list_sharing_principals for inspecting sharing, nor any precondition such as the caller needing owner rights.

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