add_rivals

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, but the description adds real behavioral context beyond them: the call only stages a change, nothing is applied until confirm_action runs, and user approval is a prerequisite. It does not say what happens to an already-tracked rival or whether the preview returns a staged payload, leaving some gaps.

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 short sentences, front-loaded with the most decision-relevant fact (PREVIEW ONLY), then the reference format, then the next step. Every sentence carries load and nothing is padded.

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 2-parameter, no-output-schema tool, the description covers the staging semantics, the apply path, and the reference syntax. What is missing is the appId format expectation and edge-case behavior (duplicates, existing rivals), but the essentials an agent needs to call it correctly are present.

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 50%: rivals carries an example, appId carries nothing. The description usefully states the canonical reference syntax (ios:<App Store id> / android:<package>), which reinforces the rivals format, but it adds nothing about appId's expected value or format. Baseline 3 is appropriate given the partial coverage remaining.

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: 'add manual competitors to an app.' The word 'manual' and the naming of rival references distinguish it from auto-discovered rival tools like get_rival_market, and the add/remove/get_rivals sibling family is easy to disambiguate. It stops short of explicitly naming a contrasting sibling, so 4 rather than 5.

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?

'PREVIEW ONLY' plus 'Apply with confirm_action after the user approves' tells the agent exactly what this call does versus what the follow-up call does, and names the sibling confirm_action explicitly. It gives no exclusions (e.g., when not to add a rival), so it is clear context rather than full when/when-not guidance.

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