update_deployment

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

Annotations already mark this as a mutating, non-idempotent call, and the description adds two material behavioral facts beyond them: the operation is Enterprise-gated (403 on non-Enterprise plans) and secret rotation returns the new secret only once in this transcript, requiring immediate secure storage. That one-time disclosure is a high-stakes trait an agent must not miss. No contradiction with annotations.

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, sequencing, the one-time secret warning, and the error condition each occupy one purposeful sentence, properly front-loaded. The only flaw is that 'Enterprise-gated' appears twice, a redundant token cost in an otherwise tight description.

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 an 18-parameter nested-object tool, the description covers the essential operational surface: what types of updates are possible, the prerequisite inspection call, the critical one-time secret behavior, and the plan-gating error. The output schema covers return values, and annotations cover the safety profile, so nothing operationally critical is 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?

With 100% schema description coverage, the baseline is 3 and the schema already documents each of the 18 parameters. The description adds an organizing frame — workspace updates, JWT-sub allowlist updates, and auth-secret rotation — that groups the parameter space into update modalities, and it flags rotate_auth's special one-time-return behavior. This is meaningful value above the schema baseline, though it adds no per-parameter syntax detail.

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 + resource ('Update a registered Gateway deployment') and enumerates three distinct update modalities: workspace access, JWT-sub access, and auth-secret rotation. It clearly differentiates from its sibling deployment tools (register_deployment, archive_deployment, get_deployment) by scope. Plan-gating and the 403 outcome further pin down what this call is for.

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 explicit sequencing guidance — 'Use get_deployment first to inspect current settings' — which tells the agent when in a workflow this tool belongs. It does not, however, state explicit exclusions such as 'use register_deployment to create a new deployment' or 'use archive_deployment to remove one,' so alternatives are not fully spelled out.

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