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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful output behavior ('Returns metadata only', 'Returns a local CLI command when a secret is involved'), which tells the agent no secret material comes back. There is mild tension, though: the description implies set does not replace active credentials, while destructiveHint=true and the required expected_version suggest an in-place update path — the description understates that.

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?

Four short sentences, front-loaded with the action, then the exclusion rule, then the two return-shape facts. No filler and nothing buried.

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, the description correctly covers the return shape (metadata only, CLI handoff for secrets), so the agent knows what comes back. It does not mention the optimistic-concurrency role of expected_version or the retry semantics of idempotency_key, but the schema documents both, so the gap is minor.

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 86% and the schema itself explains source semantics, secret_name applicability and idempotency_key reuse, so the schema carries the load. The description adds no parameter-level detail beyond what the enum descriptions already say, which is the expected baseline here.

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 and resource — saving a single credential value or Doppler reference — and the word 'one' implies no bulk write, which separates it from a listing tool like summer_credentials_list. It does not explicitly contrast itself with the sibling set as a whole, so it stops short of a 5.

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?

Explicitly routes the agent away for the replacement case: 'Replacing an active credential needs credentials.replace.' That is a real when-not rule. However, that referenced tool is not present in the sibling list, and there is no guidance on when to pick source=doppler versus source=local_value beyond the schema's own enum description.

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