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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds a substantively new behavioral fact not in the annotations: returned values are never exposed, which is critical for an agent deciding whether this call satisfies a secrets request. It stops short of describing result volume or ordering.

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 short sentences, front-loaded, with the security caveat placed where it will be read. The first sentence reproduces the title verbatim, so a small amount of the text duplicates structured data rather than adding 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?

There is no output schema, and the description compensates by naming exactly which fields come back (names, sources, versions) plus the fact that values are excluded. For a two-required-parameter, fully-documented read tool, nothing an agent needs before calling is missing.

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%: both 'company' (UUID format with pattern) and 'environment' (staging/production enum) are fully documented in the schema. The description adds no scoping semantics beyond that, so the baseline 3 applies.

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 ('List') plus the resource ('saved credentials') and enumerates the returned fields (names, sources, versions), so the scope is unambiguous. It doesn't name the sibling it complements, summer_credentials_set, but the list/set contrast is self-evident from the names.

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 only implied: 'Never returns values' signals this is a metadata-only surface and that an agent needing secret material must go elsewhere, which is useful steering. There is no explicit when-to-use, prerequisite, or named alternative (e.g. summer_credentials_set), so the guidance stays at the inference level.

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