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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true, so safety is covered. The description adds real value beyond that: no notification is sent to the client, wrong records can be removed in Jobber (reversibility), and a Cotlet API key scoped to this app is required. It stops short of describing the response, but the added behavioral context is genuine.

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?

Front-loads the action and fields, then layers behavioral notes and the duplicate caveat. Every sentence carries information, though the phrasing 'It sends nothing to the client and reaches no one, so it runs without asking first' is a touch verbose for what it conveys.

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 create tool with annotations covering the safety profile and no output schema, the description supplies the key operational facts (duplicate risk, no notification, reversibility, auth). The one minor gap is that it never hints at whether the new client's ID is returned, which would help chaining calls.

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 fully documents all four fields. The description merely restates the same field list (name, email, phone, service address) without adding format or validation detail, so the baseline of 3 applies.

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 (Add/Create) plus resource (client) and enumerates the fields it accepts (name, email, phone, service address). This clearly distinguishes it from jobber_get_client and jobber_list_clients without needing to open a schema.

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 instructs the agent to 'Search with list_clients before creating' and gives the reason ('Jobber does not stop duplicates for you'), which is exactly the routing/condition guidance needed. It also clarifies the no-notification behavior so the agent knows no approval flow is triggered.

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