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

With annotations already covering readOnly=false, idempotent=true and destructive=false, the description still adds real value: the authentication prerequisite, the seal_prediction non-empty-payload constraint, the instruction to retain returned hashes/status, and an explicit epistemic caveat that a record is not proof of an intervention or scientific result. It does not explain failure/idempotency-conflict behavior in detail, so not a 5.

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?

Front-loaded with purpose, then prerequisites, then caveats; no filler sentences. Slightly dense with parenthetical enumerations but every clause carries information.

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 mutation-style, open-world tool with no output schema, the description covers inputs, auth, idempotency and the fact that hashes/status are returned and should be retained. Missing only detail on error handling or what a returned status means.

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 every parameter including the operation enum and payload constraint is already documented in the schema; the description largely restates these. It adds only the framing that payload is operation-specific, which is marginal beyond the schema baseline of 3.

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 – 'Append one step to an existing caller-identified causal trial' – and enumerates the seven possible step operations, so an agent knows exactly what the tool does and the scope of 'one step'.

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 operating context: the trial must already exist and be caller-identified, authenticated access is required, trial_id/idempotency_key are mandatory, and the same trial_id must be reused across related steps. It stops short of naming alternatives or explicit when-not-to-use conditions, so it does not reach a 5.

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