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

Annotations already declare readOnly/non-destructive, but the description adds substantial context beyond them: data is server-persisted so all clients see it, scope is resolved from the caller's API key with no cross-user access, `app_links` are user-facing deep links, and it explains how `active` vs `paused` vs stopped should be treated.

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 identity and returned field list, then usage rules. It is dense and nearly every sentence earns its place, though the field enumeration partly duplicates the output schema and adds length.

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?

Despite an output schema existing, the description covers scope, timing, status handling, and the meaning of `app_links`, leaving nothing an agent would need to call it correctly. Complete for a read-only, single-optional-param tool.

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% and the single `include_stopped` boolean is already documented in the schema. The description restates the same behavior ('pass include_stopped=true for stopped ones too') without adding new meaning, so the baseline of 3 is appropriate.

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 ('the strategies the user's agents are running') and scopes it tightly to the current user's own persisted data. It does not explicitly name or contrast with the sibling `list_strategies` or `get_strategy`, which is the one thing keeping it from a 5.

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 explicit timing ('at the start of every session' and 'before starting a strategy') plus the reason (prevent duplicate runs across sessions) and behavioral rules (resume `active` on its `schedule`, leave `paused` alone unless asked). This is when-to-use guidance with concrete operating instructions.

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