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

With no annotations, the description carries the full burden and does so richly: it discloses that every read and write in the session is redirected to the in-memory copy, that results are prefixed 'TRIAL COPY of ...', that nothing is ever saved and there is no commit, that a large copy lives in server memory, that an idle copy is purged after 2 hours with loud failures, and that the trial is scoped to this MCP session only. It even lists the tools refused while a trial is active.

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 long, but it is front-loaded with purpose and every sentence conveys information an agent needs to operate a stateful session tool correctly. Density is high with little redundancy, though it is on the verbose side; the key constraint and workflow could be slightly tightened.

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?

With no output schema and no annotations, the description fully compensates: it explains result format ('TRIAL COPY of ...' prefix), the outcomes of each action, the no-commit semantics, the memory/timeout failure modes, session scoping, and refused operations. Nothing needed to invoke and interpret it 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 the baseline is 3, but the description adds real meaning: it explains what each of the three action values does (start creates the copy, discard throws it away, status lists trials) and clarifies that the database parameter is needed for start and discard. This goes beyond the schema's terse enum labels.

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: 'Try changes on a throwaway copy of a database before making them for real.' This is unambiguous and clearly distinguished from every sibling (which act on the real database). An agent can immediately tell what this tool is for.

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?

Explicit when-to-use is given ('a risky restructure, a bulk edit, or a first attempt at an unfamiliar write'), along with the full workflow route (start -> inspect with query_aql/describe_set/get_report_data -> discard or re-apply) and the crucial guidance that there is no commit. It also names the condition under which it should be avoided (large databases consume memory).

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