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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the safety profile is covered. The description adds real context beyond that: upsert semantics ('creates or updates'), the published-build precondition, and the redeploy caveat about re-applying the same manifests. It stops short of describing failure behavior or permission requirements.

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-loads the core action, then preconditions and target selection, ending with the redeploy caveat. The final sentence is long but carries actionable guidance, so it earns its space. Slightly dense but not padded.

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 mutation tool with no output schema, the description covers preconditions, target selection, and the tricky redeploy case. It omits what a successful/failed deployment returns and any permission requirements, but is otherwise complete enough for correct invocation.

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 namespace, cluster_id, environment, inputs, and deploy_mode. The description reinforces the mutual exclusivity of cluster_id/environment and how environment is named, but adds little beyond what the schema text already states. Baseline 3 is appropriate.

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 ('Deploy') and resource ('an Application's built chart onto a cluster') with the effect spelled out as 'creates or updates the installation.' An agent can distinguish it from siblings like reconcile_application, promote_application, or redeploy_stack without opening a schema.

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?

Explicitly names the precondition ('Requires a published build'), the check to run first ('list_application_installations'), the target-selection rule ('cluster_id or environment - exactly one'), and when to propose a redeploy. Nothing about when-to-use is left to inference.

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