Store an Onshape API key pair

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

Annotations carry only a title with no read-only or destructive hints, so the description bears the full burden. It discharges most of it with 'The pair is verified against Onshape before it is saved,' which tells the agent this tool makes a network round-trip and will decline to persist invalid credentials. It does not cover overwrite behavior for an already-stored key, but the core safety-relevant behavior is disclosed.

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 sentences, each earning its place: the first states the action and differentiates it from browser login, the second gives the use condition, and the third discloses the verification behavior. The core purpose is front-loaded with no repetition of the title or schema.

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 low-complexity credential-store tool with full schema coverage and only two required parameters, the description covers purpose, usage condition, and the key verification behavior. The only gaps are overwrite semantics and the success/failure response shape, but with no output schema expected, the description is close to complete for this tool's simplicity.

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%, so the schema already documents all four parameters (access_key, secret_key, store, base_url), earning the baseline 3. The description adds marginal semantic context by pointing users to where keys originate and stating the verification requirement implies the two keys must be a valid pair.

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 and resource — 'Store an Onshape access key and secret key directly' — and adds the distinguishing phrase 'without a browser,' which separates it from the browser-based onshape_login flow. A second sentence notes the pair is 'verified against Onshape before it is saved,' further pinning down what the tool does. This is clearly differentiated from its roughly ninety siblings, none of which store credentials.

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?

The instruction 'Use when the user already has a key pair from https://cad.onshape.com/user/developer/apiKeys' gives an explicit condition for choosing this tool, and it routes the agent to the browser-based login path when that condition is absent by implication. It stops short of naming the alternative explicitly or stating when not to use it, but the condition is concrete enough that an agent can make the call.

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