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

Annotations already mark this read-only and idempotent, and the description adds significant behavioral detail: it fetches source from the PR branch with fallback to the indexed version and announces when that fallback occurs, explains why xppbp.exe cannot run (PR is uncompiled), and notes the deterministic rule set used. It also discloses required credentials and dependencies. No contradiction with annotations.

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?

The description is front-loaded with 'WHEN', then flows logically through output, limitations, trigger phrases, prerequisites, and follow-up action. While lengthy, every sentence carries useful information for tool selection and invocation; the trigger examples aid intent recognition and the technical caveats are essential for correct use. 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?

For a tool with this complexity—requiring Azure DevOps credentials, XRef index, D365-specific analysis, and interplay with sibling tools—the description covers prerequisites, fallback behavior, output structure, and integration points. The absence of an output schema is mitigated by naming the exact dimensions of review (blast radius, BP violations, impact severity). Nothing critical 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?

Schema description coverage is 100%, so the baseline is 3. The description does not elaborate on individual parameters, but the schema already documents prId, project, repositoryId, and maxDeepAnalysis clearly. The description's mention of 'each changed object' and fallback behavior adds context but not parameter-level semantics, so it neither improves nor degrades from baseline.

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 opens with a specific verb and resource: reviewing a PR that modifies X++ code or AOT objects and returning a structured code review. It clearly differentiates itself from siblings like find_error_patterns and find_callers by specifying that it produces D365-specific PR review insights covering blast radius, best-practice violations, and impact severity.

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 'WHEN:' prefix explicitly states the exact conditions for use, and it names find_error_patterns as the alternative for Microsoft rule text. It also mentions combining with ado_post_pr_comment for posting findings, giving the agent a clear workflow. This goes beyond generic context and provides actionable routing.

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