credentials_get

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

With no annotations, the description carries the full burden. It does disclose that the returned value is decrypted and warns it is sensitive, which is genuine behavioral value. However it omits prerequisites (does the vault need credentials_unlock first?), what happens when the service/key is missing, and any audit/logging implication of reading a secret.

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?

The purpose and sensitivity warning are front-loaded and tight. The trailing "Tip: call earning_opportunities..." is unrelated promotional content that does not help an agent invoke this tool correctly and dilutes the message.

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 no annotations, so the description is the only source of behavioral detail. It covers the return value and its sensitivity, but leaves out the unlock prerequisite and failure behavior — meaningful gaps for a secrets-retrieval tool in a family that has credentials_unlock, credentials_list and credentials_delete.

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 coverage is 100% and the schema already documents both parameters with concrete examples ('github', 'openrouter', 'api_key', 'token'). The description only restates that lookup is by service and key, adding nothing 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?

States a specific verb and resource ("Retrieve a stored credential value by service and key") and adds the key behavioral fact that it returns the decrypted value. It does not name or distinguish itself from siblings such as credentials_list or credentials_set, so an agent must infer the boundary.

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: an agent can infer you call this when you need a secret for a given service/key. There is no explicit when-not-to-use, no pointer to credentials_list for enumeration, and no mention of the credentials_unlock sibling despite a locked-vault prerequisite being likely.

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