manage_session

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

With no annotations, the description carries the full burden and does so well: it discloses mutation scope, that connection state persists across subsequent calls, and the concrete side effects (launching a CAD process, terminating a session, opening a browser dashboard). It stops short of failure modes, permissions, or what happens when no CAD app is installed, which is the only remaining gap.

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?

Clearly front-loaded with labeled sections (Behavior, Usage Guidelines, Actions & Parameters, Returns) that make it scannable. It is long, but the length is largely justified by enumerating ten distinct session actions; the Returns section is somewhat redundant given an output schema exists.

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?

Covers lifecycle, persistence, side effects, action catalogue, and routing to alternatives — ample for a composite session tool, and the presence of an output schema means return values need no elaboration. Missing only error/failure behavior and prerequisite conditions for connect.

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 0% and the single 'operations' parameter is an opaque string, so the description must compensate — and it does, explaining that it is a shorthand string or JSON array of session action objects, then enumerating all ten actions with their own parameters (count default 1, host, port). The only weakness is that the exact string/JSON grammar of 'operations' remains implicit.

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 ('Manage CAD application lifecycle, COM connection, viewport controls, and undo/redo history'), and the sibling-routing section explicitly separates it from manage_view, manage_files, and draw_entities. An agent can distinguish this from every named alternative 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?

Explicit 'When to Use' plus a 'Sibling Routing / Alternatives' block naming three siblings and the exact condition that selects each ('For pure camera, zoom... prefer manage_view'). This is textbook when/when-not/alternatives guidance.

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