read_form_descriptor

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

With no annotations, the description carries the full burden and largely meets it: it discloses that the engine opens the form, replays a QUERY sweep, decodes via extract_form_field_values, the value markers used, and that decorations are omitted while Cyrillic fields are covered. It is missing runtime prerequisites (whether a test client must be running) and failure behavior, but the operational detail is unusually rich.

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?

The description is an enormous wall of internal-implementation prose (splice headers, 0x97 envelopes, _enumerate_live_fields, bootstrap ack_guid) that overwhelms the agent. Much of it is implementation detail irrelevant to selecting or invoking the tool, and the key usage signal is not cleanly front-loaded.

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?

An output schema exists so return-value explanation is not strictly required, and the description does cover the two non-default modes well. But for a 7-parameter, zero-coverage, annotation-less tool it omits the meaning of host/port/manager_templates and any precondition about the live environment, leaving gaps an agent would need.

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% with 7 parameters, so the description must compensate and only partly does. It meaningfully explains open_link, enable_live, gherkin, and capture_dir ('the one-time per-form capture'), but host, port, and manager_templates receive no explanation anywhere, leaving several parameters undocumented.

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 ('Introspect a live form into a full element descriptor') and names the equivalent ('the get_form_analysis equivalent'), so the core capability is identifiable. The distinction from data-reading siblings like read_form_value is implied by 'descriptor' rather than stated explicitly, and the intent is partially buried under implementation jargon.

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?

The description explains what enable_live and open_link do ('introspect ANY form by its nav-link') and the SCOPE caveat that decorations are omitted, which implies when this tool is and isn't appropriate. However it never explicitly compares itself to the many sibling readers (read_form_value, assert_form_value, read_record), so the agent must infer the boundary.

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