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

Beyond the readOnly/destructive annotations, the description discloses several non-obvious traits: it never invokes add/init or executes downloaded source, unknown upstream metadata is preserved, upstream items are unverified reference evidence, and an item can be inspectable while its init acquisition is unsupported. This is exactly the added context annotations cannot 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?

The core action and the snapshot-field rule are front-loaded, and most sentences carry distinct information. The closing sentence about an inspectable example with unsupported init is a useful but slightly repetitive restatement of the unverified-reference point.

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?

With an output schema present, return shapes need not be explained, and the description covers safety, snapshot-field grouping, and evidence trustworthiness. The gap is the individual snapshot parameter meanings, which remain undocumented given the low schema coverage.

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 20% (only `name` is described, and thinly as 'name (path)'), so the description must compensate. It does so meaningfully with the all-or-nothing rule for the four snapshot fields (sourceCommit, registryOrigin, inventorySha256, cliArtifactSha256) versus omitting them to inspect current state. It still doesn't explain what each hash/origin field represents, so not a 5.

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 opens with a specific verb+resource: 'Inspect one exact external registry item manifest, including examples.' That distinguishes it from the listing/search siblings, though it never names `search_registry_items` or `acquire_registry_item` directly, so the boundary is inferred from 'one exact' rather than stated.

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 a concrete usage rule: supply all snapshot fields from discovery together, or omit all to inspect current, plus a directive to 'inspect actual source and requirements before adaptation.' What's missing is explicit routing to alternatives — acquire_registry_item and search_registry_items are never mentioned even though they are the natural next/previous steps.

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