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

With no annotations, the description carries the full burden, and it delivers: it discloses the response envelope, the 7-field compact summary shape, the 250-per-page cap, the non-auto-paging behavior, and the paging.hasMore/nextOffset protocol. It also flags the compact mode's ~15x size reduction for scanning workflows.

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?

Multiple sentences, but each conveys a distinct, actionable fact: purpose, workflow, return shape, paging protocol, and scoping preference. The most general information is front-loaded before the paging caveats. 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?

Given no output schema and no annotations, the description must define return values and call behavior itself, and it does: envelope, field list, paging loop, and performance hint. An agent knows what to expect and how to page correctly on the first call. The only omitted details, like error cases, are secondary for this read/list tool.

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?

Input schema already documents all six parameters with 100% coverage, so the baseline is 3. The prose adds operational meaning beyond the schema by advising scoping with sectionId/suiteId over paging the whole project and connecting offset to paging.nextOffset. This elevates it slightly above 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?

Opens with a specific action and resource, 'List test cases in a TestRail project', and immediately narrows scope with suite/section. It positions itself against testrail_get_case and testrail_create_case by stating the exact workflow it feeds. This is enough for an agent to distinguish it from the main siblings despite not naming testrail_find_cases.

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?

Explicitly tells the agent when to reach for this tool: to discover case ids before testrail_get_case and to check existence before testrail_create_case. It also gives a concrete strategy, preferring scoped sectionId/suiteId calls over paging the entire project. The paging warning tells the agent how to complete the operation safely.

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