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

Adds real behavioral context beyond the annotations: non-idempotency ('calling twice creates two dispatches'), the push-notification side effect tied to send_notification, and the hard limit that media fields cannot be pre-filled. With destructiveHint=false and openWorldHint=true already declaring the safety profile, this is strong supplemental detail. It does not say what the response contains (e.g., the new dispatch id), which keeps it from a 5.

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-loaded with the 'WRITE:' marker and every clause carries information, with no filler or restatement of the title. It is delivered as one dense semicolon-chained block rather than being segmented by concern, which slightly hurts scanability.

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 12-parameter mutation with no output schema and only coarse annotations, the description covers the authoring decisions an agent must make: which type, which prerequisites, what happens without an assignee, and what cannot be pre-filled. Return shape and the less common scheduled-only parameters are left to the schema, which is acceptable given 100% coverage.

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%, so baseline is 3; the description earns above that by explaining the interaction between dispatch_type and the scheduled_* fields and by flagging the media-field exclusion for the responses array, which the schema does not state. It does not touch reminder_interval, send_calendar_invite, or department_id defaults, leaving those to the schema.

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 the specific verb and resource ('WRITE: creates a dispatch') and immediately defines what a dispatch is ('a job that appears on the assignee's mobile device'), which is the key disambiguation against the read-side siblings like gocanvas_get_dispatch and gocanvas_list_dispatches. An agent can identify this as the creation path without opening the 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?

Explains the two dispatch_type branches and the conditions each imposes (immediate vs scheduled needs scheduled_at and scheduled_end), notes the optional assignee_id behavior, and points to gocanvas_get_form for entry ids. It stops short of an explicit 'use this instead of X' routing statement against siblings, but the context is clear.

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