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

Beyond the annotations (all false), the description discloses an important behavioral trait: steps are copied into the run so later checklist edits do not affect an existing run. It also adds useful context about being free and uncapped, which helps an agent decide to proceed. It does not contradict annotations.

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 sentences with no filler. The primary purpose and output are stated first, then the copy-on-start behavior, then the capacity policy. Every sentence earns its place.

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 5-parameter creation tool with no output schema, the description covers the main outcome (returned run ID), a critical behavioral caveat (copy semantics), and usage context (free/uncapped). It does not explain error cases or idempotency, but annotations and schema already provide reasonable guidance.

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 80%, so the schema already documents most parameters. The description adds no new parameter-level meaning, and the 'note' parameter remains only length-constrained. This is an acceptable baseline given high schema coverage.

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 clearly states the specific action ('Start a dated run'), the resource (a checklist), and the key output (RUN-YYYY-NNNN id). It also distinguishes this from the sibling run_* tools by focusing on creation rather than viewing, deleting, or signing off.

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 implies when to use this tool: when starting a new dated run of a checklist. It provides a strong usage signal ('Runs are free and never capped') but does not explicitly contrast with alternatives like run_show or run_list, nor state any when-not-to-use conditions.

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