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: required permissions (memory:approve, org:admin), idempotence/conflict behavior, per-type accept semantics (runs held tool call as a person, applies ontology change, retires older fact), that reject writes nothing, and the full decider-rule matrix with human_required/console_required reasons.

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 action and permission, and every clause carries substantive behavioral information rather than filler. It is dense and clause-heavy, making it harder to scan than it needs to be, but little of it is expendable for a tool with this much branching behavior.

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, yet the description still usefully documents the failure shape (ok=false, reason=conflict/human_required/console_required). Combined with full permission, decider-rule, and per-type semantics coverage, an agent has everything needed to invoke it correctly.

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 baseline is 3. The description adds genuine meaning beyond the enum by explaining what each decision value actually does per review type, though it says nothing about the optional 'note' parameter beyond what the schema already states.

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 opening sentence states a specific verb triad (accept/reject/skip) plus the exact resource (one pending review) and its precondition (needs memory:approve). It is immediately distinguishable from siblings like review_list (enumeration) and review_policy_set (configuration).

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?

It richly explains the consequences of each decision per review type and the error path when the review is no longer pending (ok=false, reason=conflict). It references review_list for sourcing the review_id, but never explicitly frames when to choose this over adjacent tools such as agent_run_hitl_decide, which it mentions only as a downstream effect.

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