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

Goes well past the annotations by disclosing the key behavioral trait of a write tool with no idempotency guarantee: it appends a new note on every call, never replaces or deletes, and must not be retried blindly after a timeout. It also names the underlying endpoint (POST /v1/customers/{id}/notes), giving the agent a model of the side effect it is triggering.

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?

Three short sentences, front-loaded with the WRITE marker and the core action, followed by the non-idempotency warning and then the endpoint. Nothing is padded and the most decision-relevant fact (every call adds a note) appears early.

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 write tool with no output schema, the description covers the action, side-effect semantics, retry hazard, and endpoint. What it lacks is whether notes are visible to customers vs. staff-only, any required permission scope, and what the call returns — minor gaps but relevant to an agent deciding whether to invoke it.

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 50% — only `note` is documented in the schema, and `customer_id` is bare. The description implies `customer_id` targets a customer profile and that `note` is staff-authored text, but it adds no format, length, or identification detail (ID vs. external ID) beyond what the schema already conveys. A 3 reflects that baseline.

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?

"WRITE: add one staff note to a customer profile" gives a specific verb (add) and resource (staff note on a customer), and the "WRITE:" prefix plus the append-only phrasing separates it from the read-side moego_list_customer_notes sibling. An agent can identify this as the create-side note tool without opening the schema.

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?

Explicitly redirects to moego_list_customer_notes after a timeout, which is a concrete when-not/alternative pairing. It does not, however, say when an agent should add a note at all or how this relates to other write operations on a customer, so the guidance is situation-specific rather than complete.

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