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

Annotations already declare the safety profile (readOnly=false, destructive=false, idempotent=true), yet the description still adds substantial behavioural detail beyond them: stale or unsupported edits are rejected, ambiguous intent triggers an engineering clarification, the operation is durable and returns a new revision plus a fidelity report, and the old design is unchanged. It closes with explicit constraints (never alter read-only recognised features, never discard exact source bodies to force an edit), which tells the agent how failures arise and what the tool refuses to 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?

The purpose is front-loaded in the first clause, and each subsequent sentence adds a distinct operational fact (intent mapping, ID sourcing, scope inspection, rejection behaviour, return semantics, constraints) with no filler. It is dense and slightly over-packed with domain jargon, but nothing is redundant.

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 non-destructive, idempotent mutation with nested parameters and an output schema, the description covers the essentials an agent needs to call it correctly: where the two required IDs come from, how parameters versus instruction are consumed, what happens on stale or ambiguous input, and the follow-up poll. The unmentioned tolerance_mm and any permission prerequisites are the only notable omissions.

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 coverage is 0%, so the description carries the burden and mostly does: it maps reconstruction_id to reconstruction_artifact_id and expected_parent_sha256 to reconstruction_sha256 from a prior operation, explains that instruction is model-interpreted and limited to Design/Studio sessions, and clarifies how shared controls propagate across components versus input-group membership. Only tolerance_mm is left undocumented, which is the sole gap.

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 opens with a specific verb+resource ('Edit a saved CAD reconstruction') and immediately scopes it to explicit, qualified parameter values while preserving the source and parent revision. That distinguishes it from reconstruct_cad (creation) and get_cad_reconstruction (read) without needing to name them. It falls short of a 5 only because the qualification 'explicit qualified parameter values' is jargon the agent must decode.

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 a clear routing rule for the two input modes: map intent to parameters yourself, and use free-text instruction only for Design and Studio sessions, where Gradient Dynamics' design model interprets it. It also directs the agent to poll get_operation afterwards and to inspect verified parameter scope before editing. No explicit when-not-to-use case against reconstruct_cad, but the operation framing implies it.

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