get_lever_decisions

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

With no annotations, the description carries the full burden and does so richly: it states read-only behavior, newest-first ordering, per-entry composition, null semantics for pre-upgrade entries, and empty-state behavior until the tick runs. This far exceeds minimal behavioral disclosure.

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?

The description is a single dense paragraph but front-loads the core purpose and then systematically enumerates entry fields. It is longer than minimal, but the complexity of the returned data justifies the detail; it remains organized and readable.

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?

Given there is no output schema and the tool returns highly structured historical data, the description is remarkably complete: it covers ordering, field contents, null behavior, and empty-state semantics. No critical behavioral or return-value aspects are left obscure.

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 100%: projectId and days are both described in the schema. The tool description adds no parameter-level detail beyond the schema, 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?

The description opens with 'Read-only history of the project's daily lever-tick decisions, newest first,' which clearly identifies the verb (read/get), resource (lever-tick decisions), and scope (daily history per project). It differentiates from sibling tools like run_lever_tick and get_lever_state by emphasizing historical read-only access.

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 description clearly establishes the tool's context: it is for inspecting past daily lever-tick decisions and explicitly notes 'Empty until the tick has run at least once,' setting expectations for when results exist. It does not explicitly name alternatives or provide when-not-to-use guidance, but the read-only history framing makes the appropriate use case clear.

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