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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it delivers richly: it states side effects (creating a child item, blocking the parent), negative behaviors (does not send/publish/spend/delete/grant), and the downstream workflow ('Human or manager marks the child done, then performs the gated action'). This prevents the critical mistake of assuming an approval-gating tool performs the action itself.

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?

Three sentences with zero filler: core action front-loaded in sentence one, non-actions and workflow in sentence two, routing decisions in sentence three. Every sentence earns its place, and the most decision-relevant constraint (non-performance) comes early.

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?

Complete for a moderate-complexity tool (5 params, 4 required, output schema present). Purpose, side effects, non-behaviors, approval workflow, and sibling routing are all covered. Return values need no explanation since an output schema exists, and the negative list preempts the main misuse case.

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%, so the baseline is 3. The description adds genuine value to the gate parameter by mapping specific gate values to superseded sibling tools (gate=publish replaces file_publish/storage_publish; gate=destructive replaces memory_forget), directly informing correct parameter selection beyond what the schema's named-gate list provides.

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 opens with a specific verb+resource statement: 'Create an item_type=approval child and block the parent.' It explicitly names the sibling tools it replaces (file_publish, storage_publish, memory_forget) and lists non-actions ('Does not send, publish, spend, delete, or grant'), making it clearly distinguishable from the large sibling set.

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?

Explicit routing guidance is provided: 'Agent seats must call this with gate=publish instead of file_publish / storage_publish, or gate=destructive instead of memory_forget.' The 'Does not...' sentence further clarifies when this tool merely requests rather than performs an action, giving the agent clear when-to-use and when-not-to-use signals.

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