prune_skills

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

With no annotations supplied, the description carries the full burden and does well: it states files are moved not deleted, that they remain fully recoverable in .agents/.archive/, and that the default run is a read-only preview. Gaps remain around whether the archive can be restored through any tool, what happens on name collisions, and how 'detected project tech stacks' determines candidates.

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, front-loaded with the action and destination, then safety, then the confirmation requirement — a logical order an agent can scan quickly. There is mild redundancy between 'Safely prunes' and 'Non-destructive', but no sentence is wasted.

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 mutation tool with zero annotations and no output schema, the description covers the essentials: what is moved where, recoverability, and the dry-run-by-default contract. It does not describe the shape of the preview response or the interaction with keep_skills, which an agent would need to interpret results fully.

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 100%, so the schema already explains confirm, keep_skills, and project_path, making 3 the baseline. The description reinforces the confirm default-to-preview behavior but never mentions keep_skills, the one parameter whose override semantics (pinning skills not auto-detected) would benefit from narrative explanation.

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 description names a specific verb and resource ('prunes ... QA skills from .agents/skills/') plus the exact mechanism ('archiving them to .agents/.archive/'). That distinguishes it immediately from siblings like list_skills, install_skill, and sync_workspace_skills, which read, add, or sync rather than remove.

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 gives clear operational context: a preview is returned unless the caller sets confirm: true, so the safe default path is spelled out. It stops short of naming alternatives (e.g. use list_skills to inspect candidates before pruning) or stating when pruning should not be attempted.

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