override_verdict

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

Annotations already flag destructive=true and idempotent=true, but the description adds information they cannot carry: the required can_override_verdict permission, that an override event is written with the supplied reason, and that tasks trigger board plus Slack side effects on the bound Project V2 card and channel. Those side effects are the most important thing an agent needs to know before calling a destructive tool, and they are stated plainly.

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?

Front-loaded with the action and the hard constraint, then permissions, then side effects, then routing. Every sentence carries content, though the attempts/record_commit clause is dense enough to require a second read.

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 destructive, side-effecting mutation with an undocumented schema and no output schema, the description covers permissions and side effects well but leaves critical gaps: what status values NewStatus accepts, what happens to a live claim if one exists, and what the caller gets back after the override event is written.

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 0% across 5 parameters with no enums, so the description bears the full burden — yet it only glosses Reason ("the supplied reason") and hints that EntityType distinguishes task/finding/attempt. NewStatus gets no valid-value guidance despite driving the whole operation, as_agent is never mentioned, and EntityId's required-ness and expected ID format are unaddressed.

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 — force a state change on a task or finding — plus the defining constraint (without holding its claim), which is exactly what separates it from mark_task_status and the submit_* siblings. An agent can tell what this does and where it sits in the workflow without opening the schema.

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?

Gives an explicit trigger case (a subagent's claim went stale but the work produced still needs recording, e.g. a verifier that finished after TTL), and routes two related cases away: attempts go to record_commit, and verdicts must be overridden on the parent finding. That is when-to-use, when-not, and named alternatives in one paragraph.

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