run_filter

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

Annotations already declare readOnly, idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description adds real value beyond them: it returns an evaluation token, and changed evaluations can invalidate cursors, which is non-obvious stateful behavior an agent must respect.

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 dense sentences, front-loaded with the core action and scope before the negative constraints and cursor caveat. Little waste, though the return-value and cursor sentences could be tightened.

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 nested-object tool with 20% schema coverage and no output schema, the description usefully names the return payload (qualifiers, availability, resolved context, evaluation token). However, the substantial parameter-semantics gap for rule/revision/filter_id leaves the agent under-informed about how to actually construct a call.

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 only 20%, so the description must compensate for five parameters and a deeply nested rule object — and it largely does not. It hints at cursor semantics via 'same selector and next_cursor' but never explains revision, filter_id, page_size, or the required rule fields (table/split/criteria).

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 (run) and resource (one native draft rule or saved filter) with a precise scope ('today's Eastern slate'). It explicitly separates itself from siblings by ruling out historical test (validate_filter/start_filter_research), save (save_filter), and tracking actions.

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?

'Not a historical test, save or tracking action' gives clear when-not guidance against named sibling categories, and 'Continue with the same selector and next_cursor' directs the pagination flow. It stops short of explicitly naming validate_filter as the prerequisite test step, so it is strong but not fully prescriptive.

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