reparent_blueprint

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

Annotations declare destructive=true/readOnly=false/idempotent=false, but the description goes well beyond them: it discloses the specific compile flags (delta serialization + skip-new-variable-defaults, with the crash rationale), the absence of snapshot/rollback, the partial nature of the safe variant's rollback (SCS components left renamed), and the recommended git-based restore. Strong behavioral context, though the PIE/force constraint lives in the schema rather than here.

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?

Front-loads the purpose and the safe-variant contrast, and every clause carries real information (compile flags, rollback caveat, recovery instruction, returns). However it is dense with nested parentheticals and reads as a wall of text; some tightening would improve scanability without losing substance.

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?

Covers the full call context for a destructive mutation tool: what it compiles with, the destructive/snapshot tradeoff, recovery, error conditions, and a returns block listing the output fields plus the real oracles (get_blueprint_parent, component overrides, git status). Since no output schema exists, the description appropriately documents return values and verification path.

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 blueprint_name, blueprint_path, new_parent_class and force are all documented in the schema. The description adds little parameter-level detail beyond that (it does not restate accepted class-path formats here). Baseline 3 is appropriate when the schema carries the parameter burden.

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+resource ('Change a Blueprint's parent class and recompile') and immediately names the compile flags used, and explicitly distinguishes itself from the sibling reparent_blueprint_safe. An agent can tell exactly what this does and how it differs from the safe 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?

Explicitly states what is absent here ('NO snapshot and NO rollback') and names the alternative that supplies them (reparent_blueprint_safe), plus warns about its partial rollback and prescribes git checkout recovery before re-measuring. It also states the error condition (parent already that class). This is explicit when/when-not/alternative guidance.

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