headless_command

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

No annotations are provided, so the description carries the full burden. It does disclose two real behavioral traits: passing `project` loads a .qgz first, and save=True writes changes back to disk (an implicit mutation/persistence signal). It says nothing about error behavior, permissions, or that arbitrary commands may be destructive, so the disclosure is partial for a no-annotation tool.

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 core is two tight, front-loaded sentences leading with the capability and the persistence semantics. The trailing Georgian sentence duplicates 'without the GUI' and adds no information for most agents, but the overall size is small and the important content comes first.

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 dispatcher with a free-form `params` object, no typed enum, and no output schema, the agent is left guessing the shape of `params` for each command and what is returned. The description aids discovery with an (open-ended '...') example list and covers persistence, but does not say how to enumerate the full command set or where per-command parameter shapes are documented.

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% for 4 parameters, so the description must compensate. It explains `project` (loads a .qgz first) and `save` (writes changes back), and implicitly defines `command` via the example list, but `params` — the argument dict passed to the chosen sub-command — is entirely undocumented, which is the most consequential gap for correct invocation.

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 ('run any command ... WITHOUT the QGIS GUI') and names concrete example commands (list_layers, layer_info, add_layer, export_map, run_pyqgis) that double as pointers to sibling tools, so an agent can see this is a GUI-less dispatcher. It stops short of explicitly framing the relationship to those siblings as alternatives, which keeps it from a 5.

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 'WITHOUT the QGIS GUI' phrasing implies the usage context (no GUI session available), and 'Pass `project` to load a .qgz first' gives a concrete prerequisite. However there is no explicit guidance on when to prefer headless_command over the sibling list_layers/add_layer/etc., or over headless_algorithm and headless_list_algorithms, which is the main routing decision an agent faces.

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