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

Annotations already declare a non-read-only, non-idempotent, non-destructive write, but the description adds valuable context the annotations cannot: the mandatory chat-bubble confirmation, that it writes to the customer's TestRail project, and the return shape (new case id + browse URL).

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?

Four sentences, all front-loaded: action, return value, safety gate, then parameter selection guidance. No filler or repetition of the title.

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 write tool with no output schema, it covers the operation, the return value, the confirmation prerequisite, and the two non-obvious parameter choices. Nothing an agent needs to call this correctly 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 coverage is 100%, so baseline is 3, but the description adds real semantics: customStepsSeparated produces action+expected pairs for BDD while customSteps is plain text, and refs should carry the source Jira/AzDO key to render a linkback chip. That is meaningfully beyond the schema text.

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 and resource ('Create a new TestRail test case') and the anchor parameter ('under the given sectionId'), which cleanly separates it from sibling reads/updates like testrail_get_case and testrail_update_case.

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 conditional guidance: use customStepsSeparated for BDD-shaped tests, customSteps for plain-text, and set refs to the originating Jira/AzDO key. It also mandates user confirmation before the call. It stops short of naming the sibling it replaces (testrail_update_case) for edit-vs-create disambiguation.

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