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

Annotations provide no behavioral hints beyond non-read-only/non-destructive defaults, so the description carries the burden. It discloses key mutation semantics: 'na counts as answered and never as passed', and that a step can be re-answered with the last answer standing. This is valuable and goes beyond the 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 tight sentences, front-loaded with the core action and accepted states, followed by important semantics about 'na' and overwriting. No filler or redundant restatement of the schema.

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 state-changing tool with no output schema and minimal annotations, the description covers the essential invocation context: what states are allowed, who/when attribution, the special 'na' meaning, and re-answering behavior. It does not describe the return value, but that is acceptable when no output schema exists and the operation is straightforward.

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 is 3 because the schema already documents each parameter. The description adds cross-parameter meaning by explaining how 'state' interacts with 'by'/'at', and clarifies the special behavior of 'na' beyond the raw enum description.

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 verb ('Mark'), the resource (one step in a run), and the exact allowed outcomes (pass, fail, or na). It also distinguishes this from sibling tools like run_start or run_sign_off by focusing on step-level answering rather than run-level lifecycle actions.

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 makes the usage context clear: answer a specific step in an open run, with optional who/when attribution. It does not explicitly name alternatives or say when not to use it, but its scope is unambiguous enough that an agent can route to it correctly.

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