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

Annotations already declare the write/safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), and the description adds genuinely new context: the operation is idempotent/retry-safe and no personal data is transmitted. It stops short of stating auth requirements or what the created record looks like, but it goes 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?

A single front-loaded sentence with the verb first, no filler or repetition. It is appropriately sized for a two-parameter tool, though the dense noun string ("Caspar handoff record for a project enquiry, sample request or Wallcheck") takes a read or two to parse.

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 simple two-param mutation with no output schema and annotations covering safety, the description covers what is created and the retry/no-PII traits. It omits any relationship to start_project_handoff and what the caller receives back, leaving a real ambiguity an agent must resolve before invoking.

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 50%: the idempotency_key is well documented in the schema itself. The description compensates for the undocumented next_step by spelling out its three valid values (project enquiry, sample request, Wallcheck) in prose, which helps map intent to enum. Baseline 3 is appropriate since the schema already carries the key parameter's semantics.

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 (Create a ... Caspar handoff record) and enumerates the three supported request types, so the agent knows exactly what gets written. It does not, however, differentiate itself from the sibling start_project_handoff, leaving the agent to guess which handoff tool applies.

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?

"Safely retryable" and "without submitting personal data" imply the usage context (retry-safe writes for non-PII enquiries), but there is no explicit when-to-use-this-vs-alternative guidance. With a sibling literally named start_project_handoff, this is a meaningful gap.

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