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

Goes well beyond the annotations by disclosing the quota (5 unique Dutch addresses, 10 with the user's own e-mail), the returned credential, and the once-per-conversation constraint, which is consistent with the declared non-idempotent, non-read-only profile. The 'without an account' framing clarifies that no auth is required.

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 sentences, zero filler, and the sequence is well front-loaded: what it does, what it produces, how to use the result, then when to avoid it. Every clause carries information an agent must act on.

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 single-optional-param setup tool with no output schema, the description covers the return value, its downstream consumers, the limits, and the invocation constraints. Nothing needed to call it correctly is missing.

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 100% and the schema already warns 'only if the user typed it. Never invent one.' The description still adds value by explaining the consequence of supplying the e-mail (quota doubles to 10), which the schema does not state.

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 ('Starts a free WozApi trial without an account') plus the return artifact ('returns a trial_code'), which is exactly what an agent needs to identify a setup/onboarding action. It is clearly distinct from payment-link and lookup 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?

Explicitly names the conditions for use ('Call it once per conversation') and the exclusions ('not when the user is signed in to WozApi or the connection already has a WozApi API key'). It also routes the agent forward by naming which tools consume the trial_code.

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