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

Annotations only carry the generic destructive/idempotent profile, but the description discloses non-obvious consequences: dependent ordering, filtering, searching and alias lookups stop working, and un-hiding guard values changes who can read them. It also quantifies request cost including the conditional guard check, which is real behavioral detail beyond 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?

Four short sentences, each carrying distinct information: action, data-safety scope, blast radius, refusal gate, then request cost. The most important constraint (data is untouched) is front-loaded, and there is no filler or repetition.

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 no explanation, and the description still covers the destructive blast radius, the authorization-style gate, and request cost. Nothing an agent needs to invoke this correctly is missing.

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, but the description adds genuine semantics the schema alone lacks: confirmUnguard is not just a flag but the gate that makes an otherwise-refused guard-index deletion possible. list/index semantics are left entirely to the schema.

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 ("Delete an index") and immediately scopes it against the broader data model ("Item data is untouched"), which cleanly separates it from sibling delete_item, delete_item_data, and delete_list. An agent can pick this tool without opening any sibling schema.

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 a concrete blocker: deleting a guard index is refused unless confirmUnguard is true, which tells the agent both the condition and the required flag. It does not, however, name alternatives (rebuild_index, update_index, delete_list) or say when deletion is the wrong choice versus those.

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