nucleo-guide

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds useful output-side context by listing what the guide reports (state, rules, open tasks, exit conditions), which matters since there is no output schema. It does not explain whether the supplied phase/design values merely scope the reading or alter stored state, which is the main behavioral uncertainty left open.

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 short sentences with no filler, and the usage instruction is front-loaded. But the second sentence is compressed to the point of unclarity — "then follow next" reads as a fragment whose meaning an agent must guess.

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 workflow-orienting tool with two undocumented parameters and no output schema, the definition should explain what the returned guide looks like and how the phase/design inputs relate to it. It partially covers return content but leaves the parameter contract and the phase lifecycle unexplained, which is a substantive gap for a tool whose whole purpose is orientation.

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 both parameters are undocumented, so the description must carry the burden. It never mentions the optional `design` parameter at all, and its only reference to phase is the ambiguous phrase "Phase of the site guide," which does not clarify whether `phase` (integer 0-4, optional) selects a phase to inspect or advances to it.

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?

"Phase of the site guide" names a resource (the site guide) and its phase, and the description enumerates what it surfaces: site state, phase rules, open tasks, exit conditions. However, it never states the verb clearly — it is ambiguous whether the tool retrieves the guide for a phase or sets/advances a phase, and nothing distinguishes it from governance-adjacent siblings like nucleo-gap-list or nucleo-critical-set.

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?

"Call it before writing" gives one concrete trigger point in the workflow, which is real guidance not available elsewhere in the definition. But "then follow next" is opaque — it does not say whether "next" is a phase transition, another tool, or literally the next step in the returned tasks, and no alternative tool is named for the case where the guide is not needed.

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