package_qgis_delivery

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: it discloses workspace authorization constraints, that output_dir and its sibling .zip must be new and outside the immutable run, that the consumer must download and extract the complete ZIP because the QGZ needs companion GeoPackages/styles, and the precise verification boundaries (hashes, ZIP contents, QGZ references/counts — not real QGIS rendering or surveyed accuracy). It also flags that SVG candidates are not auto-applied, which prevents a false expectation of finished output.

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 purpose, then usage, then constraints and limits; every sentence conveys a distinct constraint. Slightly dense but 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?

An output schema exists so return values need not be explained, and the description covers preconditions, side effects, and verification limits well. The main residual gap is per-parameter meaning for a 0%-coverage schema, which would help an agent populate the two required paths correctly.

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. It establishes that both parameters are paths and that output_dir is the destination whose sibling .zip must be new and outside the run, but it never names run_dir or states it is the existing completed run directory being packaged — that link is only implied.

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 and dual resource (verified QGZ projects plus a portable ZIP) scoped to 'an existing run', and explicitly contrasts with run_conversion and prepare_review_workspace, which do not generate QGZ. An agent can identify this tool without opening the 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?

Gives an explicit trigger ('when the user requests QGZ or a QGIS package') and names two siblings that will not satisfy that request, routing the agent correctly. Nothing about when to select it is left to inference.

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