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

Annotations already mark destructiveHint=true, but the description adds crucial behavioral detail: changes publish immediately to all targets, the vault cannot reveal secrets back, and omitting auth means 'unchanged' not 'cleared'. This explains real-world consequences beyond the boolean annotations and prevents a dangerous misinterpretation.

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?

Three focused sentences, front-loaded with the tool's core purpose and immediate effect. The second sentence explains the critical secret-omission behavior, and the third closes with the destination limitation and alternative. No wasted words; every sentence adds necessary operational 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?

For a mutation tool with no output schema and a nested auth object, the description is remarkably complete. It covers what changes, how propagation works, the secret-omission gotcha, and the immutability of destinationHost. It also provides an alternative path when the tool cannot be used, making it fully actionable for an agent.

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?

While schema coverage is 100%, the description enriches the meaning of parameters, especially auth: 'Omit a secret field (or the whole `auth` object) to keep the existing value' and explains why ('the vault can never show a secret back'). It also reinforces that destinationHost is permanent. This goes well beyond the schema's one-line parameter descriptions.

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: 'Rename a credential and/or rotate its secret'. It clearly distinguishes from sibling tools like create_credential and delete_credential by stating what it does (rename/rotate) and what it cannot do (change destination). This makes the tool's purpose unmistakable.

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 states when-not to use: 'The destination host cannot be changed here' and provides the alternative: 'create a new credential for a new destination.' The description also clarifies that omitting a secret means 'unchanged' not 'cleared', giving clear operational guidance. This exceeds basic usage context by naming an alternative action.

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