Has upstream released a newer version than we track?

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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds genuine behavioral value: the mechanism (reads [tool.rrt.upstream] config), the supported registries (PyPI/npm/NuGet/crates.io/Packagist), and a real failure prerequisite (network access). These traits are not visible in annotations and help an agent predict behavior and failure modes. The 'never applies a bump' line reinforces the read-only nature with concrete meaning.

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?

Three sentences, roughly 55 words, perfectly front-loaded: sentence one states the operating result, sentence two the mechanism, sentence three the constraints. Every sentence earns its place with non-redundant information, and no structured-field content is repeated.

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 tool this simple (one optional parameter, output schema present, read-only annotation), the description is nearly complete: purpose, data source, supported registries, and a network prerequisite are all covered. The only real gap is the undefined 'group' parameter semantics; return values are already handled by the output schema.

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% and the description never explicitly explains the 'group' parameter — what it selects, its format, or what the null default does. The phrase 'Reads the group's [tool.rrt.upstream] package config' weakly implies group chooses which package config to read, but that is indirect and insufficient as parameter documentation. With coverage zero, the description was expected to compensate and largely doesn't.

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, 'List upstream package versions newer than the current project version,' states a specific verb, resource, and scope. It also internally distinguishes itself from siblings like rrt_bump (which would apply the change) and rrt_version (which tracks current versions), so an agent can tell them apart without opening any other 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?

The description gives clear context — this checks upstream registries for newer versions and is explicitly read-only ('never applies a bump'). That implies a when-not-to-use boundary against mutation tools like rrt_bump, and it states prerequisites (network access, upstream config present), but it never explicitly names an alternative tool or a conditional that routes to one. Usage is implied rather than stated.

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