Search: purge

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

Annotations already declare destructiveHint=true, so the safety flag is covered, but the description adds substantial context: what is actually destroyed (search index entries only, database records untouched), the admin requirement for a full purge, and that entries stay empty until search_rehydrate runs. That is real behavioral value beyond the structured hints.

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 action, then scope, then side effects, then the caution. Every sentence earns its place and nothing is redundant filler.

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?

For a destructive mutation tool with no output schema, the description covers destruction scope, permission requirement, recovery path, and the fact that the underlying data survives. An agent has everything needed to call it responsibly.

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 entity parameter is already documented, but the description adds meaning the schema lacks: omitting ENTITY purges the entire index and is admin-only, which materially changes how the parameter is used. Marginal but genuine addition over 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 ('Purge the search index') and immediately distinguishes itself from the read-side siblings by naming search_query and search_similar and the recovery tool search_rehydrate. An agent can place it precisely without opening the 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 the key usage condition for the omitted-parameter case ('purge everything (admin only)') and the recovery route via search_rehydrate, plus an explicit 'check with the user before running it' caution. It stops short of naming a when-not-to-use alternative in the sense of a different tool to pick instead, so it's clear context rather than full routing.

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