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

Annotations already declare destructiveHint, idempotentHint and openWorldHint, and the description adds genuinely new behavioral context: the status-gated editability rule. It still doesn't say whether omitted fields are preserved (PATCH semantics), what errors a rejected edit returns, or whether the mutation re-prices or re-validates the job.

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?

Two compact sentences plus the endpoint tag; the status constraint is placed immediately after the field list where it is most useful. Nothing is repeated from the schema or annotations, and no sentence is filler.

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 nested-object mutation with no output schema and thin schema coverage, the description supplies the essential editability model. It leaves open how partial updates behave for unspecified fields and what a successful response contains, which matters given the nested pickup/dropoff contact objects.

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 only 33%, so the description must compensate, and it does: it names client_reference, package_description, and the pickup/dropoff comment and contact as the editable set, effectively documenting the low-coverage optional parameters. It adds no format or length semantics beyond what the schema already encodes for those fields.

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 ('Change allowed details') plus the exact resource (a delivery inside a job) and enumerates the editable fields, which cleanly separates it from stuart_get_job, stuart_create_job and stuart_cancel_delivery. The PATCH endpoint reference pins down the operation further.

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?

Gives a concrete usage condition: what is editable depends on delivery status, and after delivery only client_reference can be changed. It does not name an alternative tool or state what to do when a field is not editable, so it falls short of explicit when/when-not/alternatives.

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