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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), and the description adds real behavioral context the annotations lack: the deploy path creates a 'throwaway' demo with an isolated, TTL-limited lifecycle, and the outcome is a ticket showing preview URL and build state. It stops short of stating permissions or what happens on re-attach, but goes beyond the structured fields.

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 sentences, zero filler, front-loaded with the purpose before the branch conditions, and each sentence adds distinct information (purpose, routing, outcome).

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 7-param, no-required-field mutation tool with no output schema, the description adequately covers both invocation modes and the observable result. Minor gaps remain: behavior when a demo is already attached to the ticket, and permission requirements, but nothing essential to correct invocation is missing.

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?

With 100% schema coverage the baseline is 3, and the description earns a bump by grouping the 7 parameters into coherent modes (workspace_id vs application_id + pr_number + image_tag), giving semantic meaning to how parameters combine rather than just what each means individually.

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?

Specific verb+resource+target: 'Attach a demo environment to a ticket'. It explicitly names the sibling deploy_pr_demo and clarifies the relationship ('same isolated, TTL-limited lifecycle as deploy_pr_demo'), so an agent can distinguish this from lone PR-demo deployment without opening either 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?

It lays out the two mutually exclusive paths with their selecting conditions: workspace_id for attaching an existing demo, or application_id + pr_number + image_tag for deploying a fresh throwaway demo. The stated intent ('before approving it') also clarifies the context in which the tool is the right choice.

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