save_verdict

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

With no annotations, the description carries the full burden and does real work: it discloses that verdicts are validated in code against the user's own rules — quotes must be in the transcript, a YES requires a live project and an action, standing decisions cannot be broken — and that the returned verdict may be normalized before the digest shows it. The gap is failure semantics: it does not say whether a rejected verdict raises an error, returns a corrected one, or is silently dropped.

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, front-loaded with the action, then validation rules, then return behavior. Dense and mostly free of waste, though the clause about 'exactly as it checks a model's' is atmosphere more than guidance.

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?

No output schema exists, and the description does partially cover the return ('the verdict that comes back is the one the digest will show'). But for a three-required-parameter mutation with no annotations and no schema documentation, the missing parameter formats and failure behavior leave it only adequate.

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%, so the description must explain all three parameters and does not. It hints that write_up contains transcript quotes and that verdict can be 'YES', but the allowed verdict vocabulary is never enumerated and the 'video' parameter is entirely opaque — no indication whether it is an ID, URL, or title.

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: store a verdict plus write-up for one video. That is clearly a persistence operation distinct from judge_video or get_transcript. It stops short of naming the sibling it complements (judge_video), so the split of responsibility is inferred rather than stated.

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 this is the step where a judgment is committed, and it enumerates the rules that must hold before a save succeeds. But it never says explicitly 'call this after judge_video' or what to do if validation fails, leaving sequencing to inference.

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