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

With no annotations, the description carries the full burden and does so: authorization level, the human-vs-agent seat restriction with its specific error code, the console_required condition, the audit event name (org.automation.set), the ~30 second propagation delay, and where to read the current value (memory_writes in glian_status). That is unusually complete for a mutation tool.

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 purpose and the credential requirement, and every sentence adds a distinct operational fact (restriction, error codes, audit, latency, status location). The mid-sentence line breaks and code-quoting are slightly noisy but no content is wasted.

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?

An output schema exists, so return values need not be described. Combined with the full authorization, eligibility, audit and latency disclosure, an agent has everything needed to call this correctly or know it must hand off to a human.

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% and the single enum parameter's review/auto semantics are fully documented in the schema itself. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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: setting which durable memory writes require human review. It also situates itself relative to the analogous sibling org_automation_set, so an agent can distinguish it from the many other memory_* policy setters without opening schemas.

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 concrete context: requires org:admin, is human-only (agent seats are refused with human_required), and under decider=console only a console browser session is accepted. It explains preconditions well but does not frame this against alternative tools or say when a caller would prefer it over, e.g., org_automation_set.

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