Kill My Idea

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

The annotations already declare read-only, idempotent, non-destructive, and closed-world behavior. The description adds useful context beyond those annotations by disclosing that results are cached for 5 minutes and by specifying which aggregate metrics are returned.

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 short sentences with no wasted wording. The main purpose is front-loaded, and the caching note follows as a useful secondary detail.

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 zero-parameter read-only stats tool with annotations covering safety semantics and an output schema defining the return shape, the description supplies everything needed: what is counted and how fresh the data is.

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?

The tool has zero parameters, so the baseline score is 4. There is no parameter meaning to clarify in the 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 resource being retrieved: aggregate counts of ideas analyzed and outcomes killed, fixed, or shipped. This is specific enough to distinguish a read-only stats lookup from the sibling judge_idea action.

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 by describing aggregate statistics, but there is no explicit guidance on when to call this versus judge_idea or any other alternative. For a simple zero-parameter stats tool this is acceptable, though it leaves the agent to infer the use case.

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

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

Annotations already declare readOnlyHint=false, openWorldHint=true and non-idempotence, so the safety bar is lower; the description still adds real context beyond them — deterministic rubric, no generated prose, roughly one-second latency, and the exact null-field contract when needs_detail is true. The main deduction is the cryptic '10 Jev decisions in about a second', which adds noise more than information.

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 purpose, then the success shape, then the failure shape — a sensible order. The nested parentheticals (e.g. 'KILL, FIX or SHIP, shown as verdict_label KILL IT, FIX IT or SHIP IT' and '10 Jev decisions') make it denser than it needs to be.

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 single-call judging tool with three simple parameters, an output schema and full annotation coverage, the description covers purpose, both return paths, determinism and latency. Nothing an agent needs in order to invoke it correctly or interpret the result is missing.

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 description coverage is 100%, so goal, idea and do_not_archive are already fully documented in the schema, including the enum's scoring consequences. The description text itself says nothing about parameters, so it sits at the baseline rather than adding meaning.

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 ('Judge a startup or side-project idea') and immediately enumerates the exact outputs (verdict KILL/FIX/SHIP, overall score, best_signal, biggest_risk, eight scored dimensions). The only sibling, get_stats, is obviously a different concern, so an agent can route 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?

Usage is implied by the purpose rather than stated: nothing says when to prefer this over get_stats or when an idea is out of scope. The one piece of conditional guidance given is behavioral ('If the idea is too vague to judge, needs_detail is true...'), which tells the agent what a rejected input looks like but not when to call the tool.

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