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

Beyond the annotations (readOnly/idempotent/openWorld/destructive=false), the description discloses provider-specific limits (GitHub 20/page, pages 1-50; GitLab/Asana first 20 only), that requests hit the provider live and are not a snapshot, that it never writes to the provider or creates tickets, and the required scopes integrations:read and tickets:read.

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-loads the core action, then layers provider limits, the snapshot caveat, the write-safety guarantee, and the scope requirements. Every sentence adds a distinct fact with no 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?

Complete enough with no output schema and 0% schema coverage: an agent knows provider behavior, page semantics, side effects, and auth scopes. It does not say where connection_id comes from (e.g., list_ticket_integration_connections) or what an importable item looks like, but those are minor for a browse-only call.

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 description coverage is 0%, so the description carries the load. It explains the provider enum values, the meaning of page (20 items per page, 1-50, GitHub-only pagination) and the effective no-op nature of page for GitLab/Asana. connection_id is only implicitly defined as a 'saved ... connection' identifier, which is the one gap.

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 precise verb and resource: 'Read one bounded page of importable items live from a saved GitHub, GitLab or Asana connection.' The framing 'live ... not a snapshot or complete inventory' distinguishes it from snapshot-style siblings like the receipt/observation lists and from the dry-run preview that shares its domain.

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 clear operational context — it reads a bounded page of importable items per provider, with explicit per-provider page limits — so an agent knows the scope of the call. It does not, however, explicitly route to alternatives such as preview_ticket_integration_import (dry run) or commit_ticket_integration_import (apply), which an agent must infer from the workflow.

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