Request Password Reset

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

Annotations indicate this is a non-readOnly, non-destructive, idempotent operation with openWorldHint. The description adds valuable context by specifying that it sends a code (implying an external communication action) and mentions the delivery channels (email/phone). This clarifies the tool's side effects beyond what annotations provide, though it doesn't detail rate limits, success/failure responses, or whether both email and phone can be used simultaneously.

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, efficient sentence that front-loads the core action ('Send a password reset code') and specifies the target ('to the wallet's email/phone'). There is no wasted verbiage, repetition, or unnecessary elaboration. Every word contributes directly to understanding the tool's function.

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 tool with no output schema, the description adequately covers the action and parameters but lacks details on return values (e.g., success confirmation, error cases). Annotations provide good behavioral hints, but the description could better address the tool's role in the broader reset flow (e.g., linking to 'dual_reset_password_verify'). It's minimally complete given the simple operation but misses opportunities to guide the agent on next steps.

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 input schema has 100% description coverage, with clear parameter definitions for 'email' and 'phone_number'. The description adds minimal semantics by confirming these are the target channels for the reset code, but doesn't provide additional details like format requirements, validation rules, or whether at least one parameter is required. Given the high schema coverage, the baseline score of 3 is appropriate as the description doesn't significantly enhance parameter understanding.

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 action ('Send a password reset code') and target ('to the wallet's email/phone'), making the purpose immediately understandable. It distinguishes this tool from sibling tools like 'dual_reset_password_verify' by focusing on the request phase rather than verification. However, it doesn't explicitly differentiate from other communication tools like 'dual_send_notification' beyond the specific reset context.

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 a password reset is needed, but provides no explicit guidance on when to use this versus alternatives like 'dual_reset_password_verify' or 'dual_login'. There's no mention of prerequisites (e.g., whether the wallet must exist) or exclusions (e.g., not for account recovery without email/phone). Usage is contextually implied rather than explicitly stated.

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