Personalize

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

Annotations declare openWorldHint=true (an open-world tool that can create new entities) and destructiveHint=false, readOnlyHint=false. The description adds meaningful behavioral context: it explains the tool is 'proxied to api.meshtool.ai' and notes a cost of '2 MESH/call', which is helpful operational transparency. It also clarifies the tool doesn't compute the choice itself but delegates to an 'upstream model.' This adds value beyond the annotations.

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 appropriately sized at roughly three sentences, front-loaded with the core purpose before diving into parameters and implementation details. The parameter list adds practical value rather than padding. Minor redundancy exists where the parameter descriptions partially duplicate what the schema already covers, but overall it's efficient and well-organized.

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 no output schema, the description provides enough context about the expected interaction model (send user info + candidates, get back a selected/framed option). It documents all parameters, cost, and proxying behavior. For a moderately complex tool with nested objects, the description covers the key decision points an agent needs. It could note output format or error handling, but these gaps are minor given the simplicity of the tool's contract.

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 the input schema already documents all three required parameters (profile, content, goal). The description adds marginal value by briefly restating each parameter's purpose ('profile: object — what you know about the user; content: string[] — options to choose from; goal: string — what to optimize'). The goal parameter gets an example in both schema and description ('maximize trial signup'). While these reinforce the schema, the description doesn't meaningfully extend it with formatting details or edge cases, 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 clearly states the tool's purpose: 'Choose which content to show a specific user and how to present it.' It specifies the action (personalize content), the resource (specific user), and the mechanism (upstream model picks and frames the best fit). It also provides a concrete use-case: 'Use when an agent must pick one message, offer, or variant per user instead of a generic default.' This distinguishes it from generic output tools among siblings.

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 explicitly says when to use: 'Use when an agent must pick one message, offer, or variant per user instead of a generic default.' It provides clear context for appropriate usage. However, it does not explicitly name alternative tools or explain when NOT to use it beyond the implication that it's for per-user selection rather than generic defaults.

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