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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is partly covered. The description adds genuine behavioral information — that writes are monotonic (tighten-only) relative to ancestor policies — but says nothing about what happens on a rejected loosening attempt, nor about the locked/default semantics of the untouched parameters.

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?

It is short and front-loads the action, so nothing is wasted in length. However, the clipped 'People only.' fragment trades clarity for brevity and reads as an unexplained scope hint rather than a well-formed statement.

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 explained, but for a five-parameter mutation tool at 20% schema coverage the description leaves too much unspecified: the role of 'locked', what a null value means, and error behavior on a loosening attempt are all absent.

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 only 20%: just idempotency_key is documented in the schema. The description explains none of the four remaining parameters — key, node, value, locked — leaving the crucial 'locked' flag and the meaning of a null default 'value' entirely uninterpreted.

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 ('Tighten a policy') and target ('on a node'), which distinguishes it from the read-side sibling get_effective_policy and from set_budget. The trailing fragment 'People only' is cryptic and blurs the purpose slightly, keeping it from a 5.

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?

Provides one real usage constraint — the new policy may never be looser than the ancestors' — which implies this is for incremental restriction rather than setting arbitrary policy. It names no alternative tool (e.g. get_effective_policy for inspection) and gives no when-not guidance beyond that constraint.

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