run_agent

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

No annotations are supplied, so the description carries the full burden and does so: it discloses the isolation model (agents reason only over what is passed in this call), the billing consequence (each successful run consumes a paid or trial transaction, 5 free trial runs per agent), and the exact error semantics (402 means no entitlement, 402 product_coming_soon for architect). It also flags the architect agent as unpurchasable and unbuyable-as-trial, which is behavioral context an agent could not infer.

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 purpose, then prerequisites, then a scannable per-agent list, then exclusions — a sensible ordering. The architect paragraph is dense and mixes commercial instruction ('Do not offer to buy it') with technical contract, which is longer than strictly needed, but nearly every sentence carries actionable information.

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?

With no output schema, the description still states the return shape ('a Markdown report') and even the artifacts for architect (namespace design plus starter export files for HighByte, MaestroHub, Node-RED, with source bindings deferred to deploy time). For a 3-parameter, oneOf-branching tool with 33% schema coverage, the description supplies everything needed to call it correctly and interpret failures.

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 33% and 'bundle' has no schema description at all, but the description compensates fully: it states bundle is a JSON object and explicitly NOT a file path, lists the accepted keys per agent (production, downtime, quality, planned_minutes, ideal_rate_per_min, series, alarms, genealogy, notes), and explains that 'message' is the pasted hierarchy/export or next interview answer for architect while being ignored by event agents. Each enum value is individually explained, which the bare enum in the schema does not do.

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 opening sentence states a specific verb and resource ('Run one dxpert agent over data YOU supply') plus the return format ('get back a Markdown report'), and the second sentence immediately carves out what the tool is not (no plant/broker/historian connection). The per-agent enumeration lets an agent distinguish this from ask_dxpert or run_diagnostic 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?

Contains an explicit 'WHEN NOT TO CALL' block (explaining what an agent is, summarizing data you could summarize directly, invented/placeholder data) and names the prerequisite alternative ('If the user only has a spreadsheet export, call csv_to_bundle first'). It also states the precondition for calling (entitlement or active trial) and the routing rule to read GET /api/agents/catalog before offering an agent.

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