ado_git_get_pr_threads

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

The annotations already mark the tool as readOnlyHint, so the safety profile is covered. The description adds that it returns inline code comments with file paths and line numbers, but it does not mention pagination, response shape, or any additional behavior. With the readOnly annotation in place, this is adequate but not rich.

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?

Two dense sentences: the first front-loads the read-me purpose and what it returns; the second promptly routes to the relevant writer sibling. There is no filler, and the most important info appears first.

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 read-only tool with fully documented parameters and no output schema, the description tells the agent what it returns (threads, inline comments, file paths, line numbers) and which sibling handles writes. Critical aspects like the resource identifiers are already in the schema, so no essential detail 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?

The schema already provides a clear description for all three required parameters with 100% coverage (e.g., 'Repository ID or name', 'Pull request ID'), so the agent has what it needs. The tool description does not add anything meaningful about parameter semantics beyond the schema definitions.

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?

The description clearly states the specific action: 'Get all comment threads on a pull request', which is distinct from the sibling tools: it reads threads rather than creates comments. It also names the exact sibling for the complementary write action, so an agent can immediately tell this tool apart.

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?

The second sentence explicitly says 'Use ado_git_create_pr_comment to reply to a thread or add a new comment,' which tells the agent when not to use this read-only tool and directs it to the correct alternative. This is a clear when/alternative condition, matching the get_calls calibration example.

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