aiworkhub_manager_recipe_seed_plan

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

readOnlyHint=true already establishes the safety profile, so the description's real contribution is the output shape: eligible entries, withheld entries with reasons, and toolchain evidence, plus the guarantee that nothing is written. It adds meaningful context beyond the annotation but says nothing about cost, latency, or whether the preview can drift from what the real seed would do.

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?

It is front-loaded with the one-line answer before any elaboration, and every sentence contributes. The middle sentence ('The same per-project decision ... makes, measured without making it') is a little rhetorical and restates what the comparison to seed_canonical already conveyed, which keeps it off a 5.

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?

With a rich output schema present, the description need not spell out return fields, and it still summarizes them; with zero parameters there is no input contract to explain. What remains — what it does, when to reach for it, and that it is the non-mutating twin of seed_canonical — is all covered.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a param-free tool is 4. The description does note the scope is the current project, which is useful framing given no parameter carries that information.

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 lead line names a specific verb and resource ('which catalogue entries THIS project would be seeded') and explicitly positions itself against the sibling aiworkhub_manager_recipe_seed_canonical, which it names outright. An agent can pick this one over the mutating variant without opening either 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?

It states both the alternative ('the same per-project decision seed_canonical makes') and the discriminator ('measured without making it'), then gives the concrete trigger: 'Use it when onboarding a repository to see what it will get before anything is written.' The only minor omission is an explicit decoy list of when not to use it, but the safe/unsafe split is fully derivable.

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