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

Annotations only declare the safety profile (readOnly=false, destructive=false, openWorld=false); the description goes further by disclosing that the call persists last_symbols, that the first seed sends no notifications, and that later runs notify joiners/leavers gated on a user setting. That notification side effect is exactly the kind of non-obvious behavior an agent needs, though the references to 'Settings Screener in & out' and 'Terminal Run now' are opaque UI jargon rather than precise semantics.

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?

Very short and front-loaded: the action and its effects come in the first sentence, behavioral caveats second, args last. The semicolon-chained fragments ('persist last_symbols; return entered/exited') and the 'Args:' block duplicate structure rather than add prose, which keeps it tight but slightly telegraphic.

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 not be spelled out, and the two-parameter surface is small. The description covers the essential non-obvious behavior (state persistence, conditional notifications) but leaves the notification condition referenced only by an ambiguous settings label, which the agent cannot resolve on its own.

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 50%: strategy_id is fully documented in the schema, but screener_id has no schema description. The description compensates by specifying it is 'the screener UUID from list_screeners', which tells the agent both the format and the discovery path. The Args block is minimal but covers the undocumented parameter.

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 and resource ('Re-run a saved screener') plus its two observable outcomes (persist last_symbols, return entered/exited). This clearly separates it from create_screener, update_screener, and list_screeners, which the agent can rule out without opening any 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?

The screener_id arg note ('UUID from list_screeners') implies a screener must already exist, so the agent can infer the discovery-then-run flow. However, there is no explicit when-to-use vs when-not guidance, no mention of update_screener for changing criteria, and no statement about prerequisites such as whether the screener must have been seeded.

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