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

Annotations already declare readOnly=false, destructive=true, idempotent=true, openWorld=true. The description adds the genuinely valuable PATCH-style semantic — 'only the fields you pass change' — which an agent cannot derive from the annotations alone, plus the immutable-field constraint. It does not explain the destructiveHint flag's implications or any auth/rate-limit behavior.

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?

Two sentences, front-loaded with the operation class, then the most consequential behavioral fact (partial update), then the endpoint. No filler and nothing buried.

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 21-parameter mutation with no output schema and full schema coverage, the description covers the essentials: what changes, what cannot, and the endpoint. It omits any indication of the response shape or confirmation behavior, which is a minor gap given structured fields carry the rest.

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 description coverage is 100%, so the schema already documents all 21 parameters with lengths and constraints. The description's short field enumeration and the 'cannot be changed here' exclusion add only a little beyond that; baseline 3 is appropriate.

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 ('change the descriptive fields of a registered tracking') and immediately scopes it by naming what is out of bounds (tracking number, courier). The 'WRITE:' prefix and the PUT endpoint make the operation class unmistakable against siblings like create/delete/get.

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?

Usage is implied well enough — 'a registered tracking' signals the record must already exist — and it rules out changing the tracking number or courier. However, no alternative is named for those cases (e.g. delete + recreate, or a courier-change tool), so the agent must infer the fallback.

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