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

Annotations only give the generic flags (readOnly=false, idempotent=false, openWorld=true); the description adds the details an agent actually needs: credit cost per tier (40/300), that the balance is checked before anything starts, that runs take several minutes and must be polled, that the URL must be publicly reachable, and that the signup template creates a real account on the target site with the supplied credentials.

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?

Dense but front-loaded: purpose first, then templates, then cost, then constraints, then the polling handoff. Every sentence earns its place except the template glosses, which partially restate the enum descriptions already present in the schema.

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 mutation-style, credit-consuming, multi-minute operation this covers cost, balance checking, environment requirements, side effects and the follow-up call sequence. An output schema exists, so the description correctly does not spend words on return values.

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 schema already carries the baseline. The description still adds cross-parameter meaning the schema does not: that signup consumes the email and password 'you pass' in order to create the account and land on the signed-in home, and that purchase is the default that short-circuits the need for credentials.

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 first sentence states a specific verb and resource: 'Start a Menso test on a live website.' It goes further by defining what the test actually is (an AI persona on a real cloud browser attempting a task) and what the output is (a TRACES score plus a step replay), which cleanly separates it from the sibling polling tools get_status, get_findings and get_replay_link.

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?

Explicit when-to-use guidance for both templates ('purchase' needs no account; 'signup' requires email/password and continues to the signed-in home), plus explicit routing to alternatives after starting: 'poll get_status every 30-60 seconds, then call get_findings.' It also states an environment precondition (public URL, use a preview deployment, not localhost).

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