Ask the user for keys only they have

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

Beyond the annotations (openWorldHint=false, destructiveHint=false), it discloses the security-relevant behaviour: the secret goes to an Antideploy page and into encrypted variables without passing through the conversation. It also reveals that this tool alone does not finish the job — the agent must poll list_env and then call redeploy — which is exactly the kind of cross-tool behaviour an agent cannot infer from structured fields.

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-loaded with the purpose, then the security rationale, then the procedural steps and exclusions. Every clause carries actionable information — there is no restatement of the name or filler prose, despite the description being two long sentences.

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, yet the description names the return field to surface (`url`) and prescribes the complete surrounding workflow (show url, tell where to find the value, poll list_env until all names appear, redeploy). An agent has everything needed to call it and to handle the result correctly.

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 single `names` array is already documented, so the baseline is 3. The description adds real meaning by illustrating the kinds of values (Stripe secret key, bot token, AI provider key) and by constraining which names are legitimate via the platform-provided exclusion list, though it doesn't discuss batching or format specifics.

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 concrete verb+resource: obtain a link where the user pastes a secret so it lands in the app's encrypted variables. It sharply distinguishes itself from set_env/list_env by being the path for values the agent doesn't already hold, and the title reinforces it.

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?

Gives an explicit trigger ('a value that is not in the project'), explicit exclusions ('Do not ask for what the platform fills in itself — database, storage, sign-in, email variables, app address and signing secrets'), and an explicit prohibition ('Never ask the user to paste a key into the chat'). It also names the follow-up siblings (list_env, redeploy) and the order to call them.

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