Execute reviewed cross-plugin tasks

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

Beyond the annotations (destructiveHint=true, idempotentHint=false), the description discloses the critical execution semantics: validation of every request and hash before the first write, stop-on-first-failure, known receipts, unattempted indices, and no retries/rollback/continuation. This is exactly the partial-failure behavior an agent needs and cannot get from the 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?

A single dense sentence with the preconditions front-loaded (confirmed, ordered, validate-before-write) and failure semantics following. No redundant restatement of the name or title; every clause conveys a distinct constraint.

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 complex batch-mutation tool with no output schema, the description covers preconditions and failure behavior well, and 'known receipts and unattempted indices' signals the shape of a partial result. Minor gaps remain around confirm/hash-mismatch handling, but it is largely complete.

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 the schema already carries the parameter definitions (baseline 3). The description adds meaningful semantics on top: the tasks array is ordered, the count is bounded to 1–20, and the hash must match an unchanged review batch before any request fires.

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 operation (executing 1–20 ordered CRM/Community writes) on a defined resource, and the 'Confirmed' + review-hash framing distinguishes it from a preview step. It never explicitly names preview_site_batch as the prerequisite sibling, so the differentiation is implied rather than stated.

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 description makes clear this is the execution step for an already-reviewed batch ('Confirmed', 'exact review hash'), which is actionable context. It does not state exclusions or name preview_site_batch as the required prior call, leaving some inference to the agent.

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