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

Beyond annotations (idempotentHint already true), the description explains how idempotency works in practice (retain request_id on retries), states the authentication prerequisite, and clarifies the empty-dossier outcome. Minor tension: it says credentials are never tool arguments while the schema exposes a `token` parameter, which could confuse an agent about whether to pass it.

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 short sentences, front-loaded with the action, each carrying distinct information (gating condition, idempotency, scope limit, auth). The semicolon-joined final clause is dense but not wasteful.

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?

An output schema exists, so return values need no explanation, and the empty-result semantics and auth requirement are covered. However, "declared planning scope" is asserted without saying how it is declared or what happens if it is missing, and the `token` parameter's role remains undefined.

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 0%, so the description must carry all parameter meaning, but it explains only request_id (idempotency key, retained on retries). `title` is never mentioned, and `token` is left unexplained and arguably contradicted by the claim that credentials are never tool arguments.

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?

"Create an empty dossier" gives a specific verb and resource, and "Creation does not recognise facts or calculate a plan" implicitly separates it from the calculation-oriented siblings. It stops short of naming the sibling to use for calculations, but the boundary is inferable.

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?

"only when the user requests it" is an explicit gating condition, and the statement that this tool does not calculate a plan steers plan-computing work to create_planning_calculation. No explicit when-not list or named alternative, which keeps it below a 5.

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