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

Annotations only declare the safety profile (not read-only, open-world, non-idempotent, non-destructive). The description adds real behavioral context beyond them: the one-time signing key is routed to a trusted local helper and never exposed in model-visible output, and a local CLI command is returned when a secret is involved. The tension between the schema's retry-dedup framing and idempotentHint=false is not addressed.

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 short sentences, front-loaded with the action, then the secret-handling behavior, then the return behavior. Every sentence carries information and nothing is padding.

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 mutating tool with a large nested settings object and no output schema, the description covers the critical behavioral facts an agent needs: where the signing key goes and that a CLI command may be returned. It does not describe the nested settings fields or the full success response, but the schema carries most of that.

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 80% and the id, company, environment, and allowed_origins parameters are already documented in the schema. The description's 'client-chosen ID' merely restates the id parameter's existing description rather than adding new semantics, so the baseline 3 applies.

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 states a specific verb and resource ('Create an installation') and adds a distinguishing trait ('client-chosen ID') that separates it from the installations_update and installations_rotate_key siblings. It does not explicitly name an alternative tool, but the purpose is unambiguous.

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?

Usage is only implied: the client-chosen ID hints at retry-safe creation, and the secret-handling note implies this is the path for initial provisioning. No explicit when-to-use, prerequisites, or alternatives (list, update, rotate_key) are given.

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