project_prune

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

With no annotations, the description carries full weight. It discloses per-delete verification, self-protection (never prunes own project), environment constraints (lock refusal), and irreversibility (no dry-run). This is comprehensive and covers all critical behaviors.

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 dense sentences that front-load the purpose, then add constraints and side effects. No redundancy or filler; every clause earns its place.

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?

Given an output schema exists and no parameters, the description fully covers the tool's behavior, safety, and environmental constraints. An agent receives everything needed to decide when to call it and what to expect.

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?

Zero parameters, so schema coverage is 100% (no properties). Baseline of 4 applies; description adds no parameter-specific details, which is appropriate since there are none to clarify.

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?

States a specific verb ('delete') and resource ('prune projects'), defines the precise condition (owns no rows anywhere in the store), and contrasts with the caller's own project. Clearly distinguishes from siblings like actor_prune by focusing on project-level cleanup.

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?

Provides explicit exclusions: refuses under HIVE_PROJECT_LOCK=1 and never prunes the caller's own project. Implies usage for cleaning up empty projects, though it does not explicitly name alternative tools for non-empty or actor-specific cleanup.

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