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

Beyond the readOnly/openWorld annotations, it discloses non-obvious traits: results may be partial, zero hits do not prove catalog-wide absence, and returned snapshot/manifest digest/requirements/preview provenance must be preserved. It also warns that items are external candidates and not insertable cards or fidelity evidence, which prevents misinterpretation of results.

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?

Purpose is front-loaded, but the paragraph drifts into agent-process instructions ('preserve the exact returned snapshot', 'do not fabricate pins') that crowd out parameter meaning. Six dense sentences with heavy jargon; a tighter split between what the tool does and agent policy would read better.

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?

An output schema exists, so return values need not be explained, and the partiality/provenance caveats are valuable. However, for a 9-parameter tool with zero schema descriptions, the description leaves cursor paging and limit/query/tag semantics unexplained, which an agent needs to call it correctly.

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 0%, so the description must carry parameter meaning, and it only fully clarifies the four snapshot pins (must be supplied together) and the itemType=example special case. query, tag, limit, and especially cursor are left with no semantic explanation, so the compensation is only partial.

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 first sentence gives a specific verb (discover) and resource (external registry source candidates), which separates it from get_registry_item and acquire_registry_item, which retrieve rather than discover. The phrasing 'through the maintained pinned client' is internal jargon that adds little, but the core purpose is unambiguous.

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 states a clear usage condition: omit all snapshot fields to use the current organization snapshot, or supply registryOrigin, sourceCommit, inventorySha256 and cliArtifactSha256 together. It also routes the agent to refresh_registry_snapshot when no snapshot exists and flags that itemType:example does not support query/tag ranking. It does not explicitly contrast with acquire_registry_item/get_registry_item, so the sibling routing is incomplete.

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