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

Annotations already cover readOnly/idempotent/destructive, so the bar is lower, yet the description adds real value: the 1-20 item bound, the required OAuth scopes (integrations:read, tickets:read), the read-only/no-creation guarantee, and the fingerprint artifact produced for the commit step.

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 dense sentences, front-loaded with the core action and result, followed by selection format and permissions. No filler, though the selection-format clause is a little compressed for a union type.

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 3-required-param tool with no output schema, the description covers the selection encoding, the provider enum, the item limit, the permission requirements, and the downstream fingerprint use. The only real gap is explaining what a connection_id refers to.

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 0% schema description coverage the description must compensate, and it does for the trickiest parameter: it spells out the per-provider selection shapes (GitHub {id, number}, GitLab {id, iid}, Asana gid strings) that the anyOf union leaves ambiguous. connection_id is left unexplained, keeping it from a 5.

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 (re-read/preview), the resource (selected ticket integration items from the provider), the output (importable content + fingerprint), and explicitly ties itself to the sibling commit_ticket_integration_import. An agent can distinguish it from browse/commit without opening 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?

Clearly frames this as the preview step preceding commit_ticket_integration_import and tells the caller the selection must match what browse_ticket_integration_import returns. It gives strong context but never states exclusions or failure conditions (e.g., what happens if selection is stale).

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