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

Annotations already declare destructive=true, idempotent=true and readOnly=false, so the safety profile is covered. The description adds real value beyond that: it discloses the permission requirement (owner or admin seats), states that a repeat removal returns success, and instructs reusing the idempotency key on retry. It does not say whether the person's sign-in or other derived state is revoked, which is the main remaining gap.

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?

It is packed into four short sentences that front-load the operation and its seat restriction. Some phrasing is compressed to the point of awkwardness ('Assigning training stays a person's (it creates a sign-in)'), costing a little clarity.

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 two-parameter destructive mutation with no output schema, the description covers the essentials an agent needs: what is removed, where the id comes from, who may call it, and how retries behave. Only the failure-mode and post-removal side effects (sign-in/account impact) are left unstated.

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 only 50% — the id parameter has no schema description — and the description compensates by specifying that the id comes from the training_assignments read entity and identifies a single person-to-module assignment. It also reinforces the retry contract for idempotency_key, which the schema already documents, so the value is additive rather than purely duplicative.

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 states a specific verb and resource: it removes one person's assignment to a training module, and it names the authoritative source for the id (the training_assignments read entity). It also distinguishes itself from the assign direction ('Assigning training stays a person's'), though the phrase 'as Assign's Remove does' references an external product concept an agent may not know.

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 the access precondition ('owner or admin seats only'), points at the sibling direction for the opposite operation (assigning training creates a sign-in and is done elsewhere), and tells the caller to reuse the same idempotency_key on retries. There is no explicit when-not-to-use case for an already-absent assignment beyond the idempotent-success note.

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