install_integration

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

With no annotations at all, the description carries the full burden and does well: it declares the operation is a write, names the refusal conditions (read-only mode, worker context, stale plan hash), and states the post-condition that the harness must restart before tools appear. It does not address reversibility of the install or what a partial failure leaves behind, which keeps it from a 5.

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?

Four short sentences: purpose first, then safety/refusal behavior, then the operational post-condition. No redundant restatement of the tool name and no filler.

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 write tool with zero annotation coverage, the description covers the critical risks (authorization mode, worker refusal, plan staleness, restart requirement), and return values are covered by the existing output schema. The one real hole is `approve_level`, undocumented in both the schema and the description.

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 0%, so the schema contributes no meaning. The description clarifies `harness` (the target that must restart) and `plan_id` (must match a freshly computed plan), but says nothing about `approve_level`, a parameter with a non-obvious default of "dispatch" whose accepted values an agent cannot guess.

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 gives a specific verb and resource ("Install one harness") plus a precondition ("after the user approved the reviewed plan"), which implicitly contrasts with the sibling plan_integration. It stops short of naming the sibling tool or stating that only one harness per call is installed, so differentiation is inferred rather than spelled out.

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?

It states the triggering condition clearly (user approval of the reviewed plan) and lists three when-not conditions: worker contexts, HARNESS_MESH_READ_ONLY=1, and a plan_id that no longer matches a freshly computed plan. It never explicitly points at plan_integration as the required preceding step, leaving the workflow link to inference.

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