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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=false, so the safety profile is partly covered. The description adds genuinely behavioral context — that 'todo' terminates the run and that outcome is a binary ok/halted — but never explains why the tool is destructive (does it overwrite an earlier checkpoint?) or what a repeat call for the same step does.

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?

Two sentences with no padding, front-loaded with the core action and then the run-closing rule. It could be marginally tighter, but every clause carries 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 and a nested evidence object, the description covers the write semantics but omits the return value, whether evidence/errorClass are enforced conditionally on outcome, and any notion of ordering or retry behavior for a non-idempotent, destructive call. Adequate but with clear gaps.

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 baseline is 3. The description goes further by coupling each outcome value to its payload ('ok with evidence counts, or halted with an error class'), which effectively documents the conditional pairing of evidence vs errorClass that the schema leaves unstated, since neither is marked required.

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?

States a specific verb and resource ('Records the outcome of one step of a daily update run') and narrows the payload to two cases: ok with evidence counts, or halted with an error class. An agent can distinguish it from run_start/run_status/run_recap, though it never names those siblings to sharpen the routing.

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?

Usage is implied rather than stated: it must be called during a run (runId 'from run_start'), and the 'todo' step closes the run, which tells the agent when the sequence ends. There is no explicit when-to-use/when-not guidance and no mention of alternatives for reading run state.

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