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

Goes well beyond the annotations by disclosing billing behavior (BYO key first, managed wallet fallback only if funded), the immutable agent_type verification on update, and that a mismatched type is rejected. The remaining gap is update semantics for omitted fields — whether an update replaces or merges unspecified properties is never stated, which matters for an upsert with 9 fields and destructiveHint=false.

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 core definition and upsert rule before the conditional constraints, and nearly every sentence carries a constraint. It is a single very dense block, though, and the immutability and billing points would read better split out rather than embedded mid-paragraph.

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 9-parameter, nested-schema mutation tool this covers type immutability, the create/update switch, billing, tier gating, and trigger semantics; the output schema covers return values. The one substantive omission is what happens to fields left out on an update, which an agent needs before safely issuing a partial update.

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 baseline would be 3, but the description adds cross-field conditional constraints the schema cannot express: steps must be non-empty when creating a workflow agent and must be omitted for autonomous; managed_model is only valid for autonomous; when="schedule" requires a schedule with cadence-specific sub-requirements (weekly needs day_of_week, monthly needs day_of_month).

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?

Opens with a specific verb+resource ('Create or update a standing agent') and immediately defines what an agent is ({goal + tickers + schedule}). It distinguishes itself from siblings by naming run_agent (which fires runs) and by explicitly stating there is no separate update_agent, matching the save_watchlist/save_thesis convention.

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?

Explicit routing rules: omit agent_id to create, pass one to update; use run_agent to actually fire a run; delete and recreate to change agent_type. It also states the access requirement (Tier sp500+, sample rejected), which tells an agent when the call will simply fail.

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