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

Annotations already declare readOnly=false, idempotent=true and destructive=false, so the safety profile is covered. The description adds two things annotations cannot: the draft-only mutation constraint and partial-update semantics ('Only send what changed'), which tells the agent unspecified fields are preserved. It does not say what happens when a confirmed request is targeted or how errors surface.

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 short sentences, front-loaded with the action and the draft constraint, then the partial-update rule, then the follow-up call. No filler and nothing an agent must read twice.

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 non-destructive, idempotent mutation with 83% schema coverage, no output schema and annotations carrying the safety hints, the description covers when to use it, what to send and what to do next. Only the failure behavior for a non-draft request_id is unaddressed.

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 83%, so the baseline is 3 and the schema already documents request_id, access_key and most optional fields. The description earns above baseline by enumerating the four mutable parameters and adding the partial-update convention that the schema only implies through 'Field values to change'.

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) plus the exact mutable attributes (fields, region, description, urgency) and scopes the resource to a 'Bidit request that is still a draft'. The draft qualifier separates it from submit_request and create_request without the agent needing to open any 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?

Gives a real precondition ('still a draft (not yet confirmed by the customer)') and a routing hint ('After fixing validation errors, call submit_request'), plus an operational instruction ('Only send what changed'). It stops short of naming a competing tool for the non-draft case, so the when-not path is implied rather than explicit.

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