system_one_decide

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safe, non-mutating nature is clear. The description adds that it is advisory only and does not act on the decision, which reinforces the annotations without contradicting them. However, it doesn't detail side effects (none expected) or response format, but annotations cover the safety profile.

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?

The description is a single sentence with no waste: it states the core purpose (compare candidates) and a critical caveat (advisory only). All key information is front-loaded and concise.

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?

Given the tool has 7 parameters and no output schema, the description leaves out return format and details on how parameters like evidence and auto_accept are used. However, it's a decision-support tool with clear advisory role, and the schema provides structural limits (2–6 candidates, max requirements). Some gap exists in explaining the decision process, but it's sufficient for a competent agent.

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 0%, so the description must add meaning to parameters. The description mentions 'candidates', 'explicit requirements', and 'escape hatches', which aligns with parameters like candidates, requirements, and escape_hatches, but doesn't explain other parameters like evidence, priorities, or auto_accept. It provides minimal compensation for the lack of schema descriptions, so a baseline 3 is appropriate.

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 states it compares 2–6 candidates with explicit requirements and escape hatches, which is specific and conveys the resource (candidates) and action (compare/decide). It also notes it's advisory only, which distinguishes it from tools that act. However, it doesn't explicitly name sibling tools it differs from, but the advisory-only qualifier helps differentiate from gate/verify.

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 usage when comparing candidates and making a decision, but does not explicitly state when to use this vs alternatives like system_one_compare or system_one_review, nor when not to use it (e.g., for acting on decisions). It also doesn't describe prerequisites like providing evidence or candidates beyond the schema.

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