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

Annotations already declare readOnlyHint=true, and the description repeats 'This tool is read-only' rather than extending it. It does add one genuinely useful behavioral constraint: only non-sensitive project characteristics should be supplied. It says nothing about the shape of the recommendation, whether it is advisory only, or how the result should be interpreted — and with no output schema, that burden remains entirely on the description.

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?

Two tight sentences: the capability first, the safety constraint second. Nothing is padded. The only wasted clause is the read-only restatement, which duplicates the annotation.

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 pure advisory tool with 11 inputs and no output schema, the description establishes what it does and that it is safe, but not what comes back or how the inputs are weighed. An agent cannot tell whether omitting requiresRoot or needsDatabase degrades the recommendation, nor what a returned 'product and workflow' looks like.

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% across 11 parameters, so the description is the only place meanings could be explained, and it explains none of them. It names no parameter, gives no guidance on the enum values (appType, runtime, expectedTraffic) or on the booleans such as requiresRoot, customTcpPorts, or hasDockerfile, which materially change the recommendation. The phrase 'non-sensitive' is the only substantive hint, and it does not map to a specific field.

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?

A specific verb pair (analyze/recommend) applied to a concrete resource: the smallest DotMoose product plus publication workflow for a named app type. The enumerated app categories mirror the appType enum, so an agent can match input to tool. It stops short of distinguishing itself from the sibling recommend_product, which read-only listing suggests is the nearest alternative.

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?

Usage is implied by the scope ('plan how to publish' vs. quoting or signing up), but there is no explicit when-to-use or when-not-to-use statement and no pointer to sibling tools like recommend_product, quote_public_product, or list_public_products. The agent must infer the routing from names alone.

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