femm_session_open

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

No annotations exist, so the description carries the full burden, and it discloses a lot: process spawn behavior (femm_headlessw, no window, fastest), a cross-tool dependency (screenshots require headless=False), attach/host semantics, and working-directory/default/env-var behavior. It does not cover error modes or what happens when a same-named session already exists with conflicting options.

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-loaded with the core purpose and routing constraint in the first sentence, then organized into per-flag clauses. Every sentence earns its place and there is 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 5-param, no-annotation, no-output-schema session opener, the description is rich enough to invoke correctly, including defaults and the env-var-backed work_dir. Minor gaps: no statement of the return value or reuse/error behavior, but the 'session' handle convention is already established by sibling tools.

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%, so the description must compensate, and it does address most parameters: name (named engine, default 'main'), port (in the attach clause), attach, headless, and work_dir (engine cwd, default ~/femm-agent-work/<name>, env FEMM_AGENT_WORK). It adds real semantics beyond the bare typed schema, though types/format for port and work_dir remain thin.

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 opening sentence states a specific verb+resource ('Start (or reuse) a named FEMM engine') and explicitly distinguishes it from every sibling by noting that all other tools take `session` and open lazily. An agent can tell this tool apart from femm_session_close/femm_session_list without opening any 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?

It gives an explicit when-to-use rule ('call this only to choose options') and the alternative (lazy implicit open by other tools). It then routes each option: headless=True/False with the femm_save_bitmap caveat, and attach=True for an already-listening engine. When/when-not plus alternatives are covered.

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