cred_refs

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

The only annotation is destructiveHint=true, and the description never addresses write/overwrite behavior, permissions, or what the add vs list actions do. It does add useful context that credentials themselves are not stored, which is a meaningful behavioral clarification given the sparse annotation.

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 tight sentences, front-loaded with the core purpose and followed by a concrete example. No waste; the example earns its place by clarifying the 'pointer' concept.

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 no output schema and only a destructiveHint annotation, the description carries more burden than it fills: it never mentions the add/list action enum or what listing returns. For a dual-action tool with sparse annotations, this is adequate but incomplete.

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 six parameters including name, location, and action. The description's example indirectly illustrates name/location but adds no syntax or format detail beyond the schema, so 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?

The description gives a specific verb+resource: storing pointers to where credentials are documented, and explicitly carves out scope via '(not the credentials themselves)'. It is unambiguous, though it does not name any sibling to differentiate from, likely because none compete.

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 through the example ('Django admin creds are in tests/...'), which signals the intent to record references rather than secrets. There is no explicit when-to-use, when-not, or alternative tool named, leaving routing to inference.

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