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

With no annotations, the description carries the full burden and does substantial work: no token required, trials are 'untrusted data from sessions', payment comes from the builder and not Lockzone, and records are signed with a citable line. Those are exactly the safety and trust facts an agent needs before acting. It does not cover pagination, ordering, or result-size limits for the list mode.

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?

Content is front-loaded with the 'Use when' clause and every clause carries information — templates, payment, signatures, the untrusted-data warning. The execution is dense, though: long run-on sentences and a mid-sentence parenthetical listing five template names make it slower to parse than it needs to be.

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 five-parameter, four-mode tool with no annotations and no output schema, the description covers what each mode returns, the trust model, and the payment caveat. Remaining gaps are operational rather than semantic: list size, ordering, and whether closed trials are retrievable by id.

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 60%, so the description must compensate and largely does: it explains what id returns (every run plus the builder's answers), what status: open filters to, what public_key retrieves, and that report: true switches to the operator report rather than the record. Only 'target' is left to the schema, which already describes it as an origin filter.

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 concrete use case and then states the resource explicitly: it 'Lists Cold Trials' — builders asking fresh agents to try their service and report where they got stuck. That is specific enough to separate it from siblings like lockzone.service or lockzone.look. It is docked a point because the tool actually serves four different purposes (list, fetch by id, fetch by public_key, fetch report) and the opening sentence blurs them together.

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?

It gives real mode-selection guidance: no arguments to list, 'status: open' for ones you can run now, 'with id' for a single trial with all runs, 'with public_key' for that key's record, and 'add report: true' for the operator report instead. It also warns to 'Read a trial's owner proof before running it.' It stops short of naming a sibling alternative or saying when not to use this tool.

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