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

Goes well beyond the annotations: names the authorization rule (only the attacher and the project lead may change one), discloses that the response never carries the value, and explains the security posture behind it ('being shown a secret is not being given it to pass on'). It also adds an operational constraint about never repeating the value in comments/logs/MRs, which is exactly the kind of context annotations can't express.

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?

Front-loads the verb and the affected fields, then the update semantics, then permissions, then the no-leak rule — a sensible order with no filler sentences. Minor redundancy in re-explaining the 'readers' REPLACES / noReaders empties behavior that the schema already covers, and the closing sentence is long though substantive.

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?

No output schema exists, and the description covers the return value anyway ('The answer never carries the value'), along with auth requirements, partial-update behavior, and handling of the sensitive payload. For a destructive mutation tool this leaves an agent with nothing essential 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% and the schema already states that omitted fields are kept, that 'readers' replaces the whole list, and what 'noReaders' does. The description restates those facts (with emphasis) but adds little syntax or format detail beyond the schema, 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?

Opens with a specific verb and resource ('Change a credential, by the id from list_credentials') and enumerates exactly which attributes can change: name, value, readers. That makes it trivially distinguishable from create_credential, delete_credential, and reveal_credential in the sibling list.

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 the id source (list_credentials) and the partial-update rule ('only what you pass is touched'), plus the practical consequence that removing a reader never requires re-supplying the secret. It does not explicitly say when to prefer reveal_credential or delete_credential instead, so routing to siblings is implicit rather than spelled out.

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