use_credential

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

With no annotations, the description carries the full burden and does well: it discloses that the raw key is never exposed, that a decision agent gates the call by risk class, that chat 'yes' cannot approve, and that a running verdict means the call is already in flight. It omits error handling, rate limits, and return-shape details.

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?

Purpose is front-loaded and every clause carries operational content (approval flow, verdict handling). The dense run-on semicolon style is harder to parse than it needs to be, but there is little wasted text.

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 complex tool with an approval workflow, 8 params, no annotations, and no output schema, the workflow side is well covered but the parameter side is not. An agent still cannot tell what api_key, body, content_type, or agent should contain.

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 0% across 8 parameters, yet the description only explains 'justification' (what you need it for) and alludes to 'credential' via 'one of the user's keys'. It leaves body, agent, method, content_type, and especially the api_key-vs-credential distinction completely undocumented.

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 ('Call a service with one of the user's keys') plus the key constraint ('without seeing it: Commons makes the request and returns the response'). Clear enough to distinguish from credential-management siblings, but it never names the sibling 'call', which an agent may confuse with this tool.

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?

Provides real routing rules: sound reads are allowed, writes need the user's request, risky ones wait for the user, and it prescribes the approve_url / approval_status(question_id, wait=120) flow. It also tells the agent not to resend when verdict is 'running'. It stops short of naming an alternative tool to use instead.

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