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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false; the description goes beyond them by disclosing the actual side effects (decisions are persisted, proposals are filed only if they clear the gate) and the required credential level ('Developer or owner key'). It does not warn that repeat runs create additional records, which is the main residual risk for a non-idempotent mutation.

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?

Three dense sentences, front-loaded with the action and its effects, then follow-up reads, then auth and the REST equivalent. Every clause carries information; the packing is slightly heavy but there is no filler.

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 steps in and describes the return ('Returns the cycle') plus where to read the derived artifacts (list_proposals, get_mandate). Combined with the side-effect and auth disclosures, an agent has everything needed to invoke it correctly.

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 only 50% (api_key is documented, mandate_id is not), so the description carries extra burden. It partially compensates by specifying the auth tier for api_key and by implying mandate_id via 'the mandate's cycle' and the /mandates/{id}/run endpoint reference, but it never states mandate_id's meaning or expected value directly.

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?

Names a specific action (run the mandate's cycle now) and enumerates the concrete consequences: sweep strategies on the household's current version, store each decision, file proposals that clear the gate. This is far more than a restatement of the name and clearly distinguishes it from read-oriented siblings like get_mandate or list_proposals.

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?

Establishes the context of use ('record a manual trigger' — i.e. an out-of-band invocation rather than a scheduled cycle) and routes the agent to list_proposals and get_mandate for follow-up reads. It stops short of naming an explicit alternative (e.g. run_model for a single model) or stating when not to trigger a cycle.

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