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

Annotations already carry readOnly/idempotent/non-destructive/openWorld=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: filters intersect, coverage reports archive availability, exports are paginated and identify page plus dataset snapshot, and snapshot/compare IDs should be reconciled across pages.

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?

Dense and front-loaded: the mode list leads, followed by behavioral constraints. Most clauses earn their place, though the first sentence is a long run-on enumeration that could be broken for clarity.

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 complex multi-mode tool with nested objects and an output schema, the description covers modes, export/pagination semantics, and the iwac:// schema-discovery URI. Combined with annotations and the output schema, an agent has enough to invoke it correctly, with only subset/limit semantics left implicit.

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?

Top-level schema description coverage is 0%, so the description must compensate. It effectively documents the `mode` enum values and the cross-parameter dependency for `compare`, but says nothing about `limit`, `offset`, or the `subset` enum members, leaving part of the parameter surface unelucidated.

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 names a specific dispatchable resource ('Selection workbench') and enumerates all nine modes it supports, plus the exports it can produce. An agent can tell this is a corpus-exploration router, though it does not explicitly contrast itself with the many search_*/list_* siblings, leaving mode-to-sibling routing to inference.

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 gives one hard usage rule ('compare (requires comparison)') and frames each mode's intent (coverage = availability, exports = paginated). However, it never states when to reach for explore_corpus rather than search_articles, search, or the get_* tools, so the alternative-selection guidance is only implied.

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