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

Goes well beyond the annotations: discloses a hard auth requirement (JWT, not rk_ key), atomic all-or-nothing semantics ('one foreign item refuses the whole call (403 not_yours) and nothing is written'), a 100-item cap per pack, and the return value ('Returns the pack'). This is exactly the operational detail readOnlyHint=false/destructiveHint=false do not convey.

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-loads the auth constraint, then the operation, then the item shape, then failure/limit behavior in dense but waste-free sentences. Every clause carries actionable 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?

Covers auth, payload shape, ownership validation, error code, size limit, and return value. No output schema exists, and the description supplies the return fact the agent would otherwise lack.

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?

With 0% schema description coverage, the description compensates well: it explains that add/remove are lists of {kind, ref}, enumerates kind values (rig|skill|harness|agent), and defines ref as a registry listing id or a Forge agent id. Only pack_id is left implicit, which is self-evident from the required field name.

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 pair and resource ('Change YOUR pack's items: add / remove'), scoping it to the caller's own pack so it is distinguishable from pack_get/pack_create. An agent immediately knows this is the pack membership mutation tool.

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 a clear precondition (JWT required, never an rk_ key) and a when-not condition (only items you own may be added; foreign items are refused), which is real usage context. It does not, however, name a sibling alternative such as pack_get for read-only inspection or registry_search for finding the ids to pass in.

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